diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/args.json b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/args.json new file mode 100644 index 0000000000000000000000000000000000000000..210bdc89d37c1e60b3835d392890a233485cb3cd --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/args.json @@ -0,0 +1,718 @@ +{ + "use_ray": false, + "ray_exp_name": null, + "device_groups": null, + "model": "checkpoints/Qwen3-VL-30B-A3B-Instruct", + "model_type": "qwen3_moe_vl", + "model_revision": null, + "task_type": "causal_lm", + "torch_dtype": "bfloat16", + "attn_impl": null, + "new_special_tokens": [], + "num_labels": null, + "problem_type": null, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_type": "default" + }, + "device_map": null, + "max_memory": {}, + "max_model_len": null, + "local_repo_path": null, + "init_strategy": null, + "template": "qwen3_vl", + "system": null, + "max_length": 8192, + "truncation_strategy": "delete", + "max_pixels": null, + "agent_template": null, + "norm_bbox": null, + "use_chat_template": true, + "padding_side": "right", + "padding_free": true, + "loss_scale": "default", + "sequence_parallel_size": 1, + "template_backend": "swift", + "response_prefix": null, + "enable_thinking": null, + "add_non_thinking_prefix": true, + "dataset": [ + "highlight_batch1", + "highlight_batch2", + "highlight_batch4_part1", + "highlight_batch4_part2", + "highlight_batch4_part3", + "highlight_batch5_part1", + "highlight_batch5_part2", + "highlight_batch5_part3" + ], + "val_dataset": [], + "cached_dataset": [], + "cached_val_dataset": [], + "split_dataset_ratio": 0.0, + "data_seed": 42, + "dataset_num_proc": 8, + "load_from_cache_file": false, + "dataset_shuffle": true, + "val_dataset_shuffle": false, + "streaming": false, + "interleave_prob": null, + "stopping_strategy": "first_exhausted", + "shuffle_buffer_size": 1000, + "download_mode": "reuse_dataset_if_exists", + "columns": {}, + "strict": false, + "remove_unused_columns": true, + "model_name": null, + "model_author": null, + "custom_dataset_info": [], + "quant_method": null, + "quant_bits": null, + "hqq_axis": null, + "bnb_4bit_compute_dtype": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "max_new_tokens": null, + "temperature": 0.9, + "top_k": 50, + "top_p": 0.9, + "repetition_penalty": 1.0, + "num_beams": 1, + "stream": false, + "stop_words": [], + "logprobs": false, + "top_logprobs": null, + "structured_outputs_regex": null, + "ckpt_dir": null, + "lora_modules": [], + "tuner_backend": "peft", + "train_type": "lora", + "adapters": [], + "external_plugins": [], + "seed": 42, + "model_kwargs": {}, + "load_args": false, + "load_data_args": false, + "packing": false, + "packing_length": null, + "packing_num_proc": 1, + "lazy_tokenize": true, + "custom_register_path": [ + "ms-swift/custom_video_dataset_base.py" + ], + "use_hf": false, + "hub_token": null, + "ddp_timeout": 18000000, + "ddp_backend": null, + "ignore_args_error": false, + "use_swift_lora": false, + "freeze_llm": false, + "freeze_vit": true, + "freeze_aligner": true, + "freeze_parameters": [], + "freeze_parameters_regex": null, + "freeze_parameters_ratio": 0.0, + "trainable_parameters": [], + "trainable_parameters_regex": null, + "adapter_load": null, + "target_modules": [ + "all-linear" + ], + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias": "none", + "lora_dtype": null, + "use_rslora": false, + "rlhf_type": null, + "ref_load": null, + "ref_adapter_load": null, + "beta": null, + "rpo_alpha": null, + "reference_free": false, + "label_smoothing": 0.0, + "f_divergence_type": "reverse_kl", + "loss_type": null, + "desirable_weight": 1.0, + "undesirable_weight": 1.0, + "calculate_KL": null, + "center_rewards_coefficient": null, + "teacher_model": null, + "teacher_model_type": null, + "teacher_model_revision": null, + "lmbda": 0.5, + "seq_kd": false, + "offload_teacher_model": false, + "sft_alpha": 0.0, + "generation_batch_size": null, + "steps_per_generation": null, + "num_generations": 8, + "num_generations_eval": null, + "max_completion_length": 512, + "importance_sampling_level": "token", + "tau_pos": 1.0, + "tau_neg": 1.05, + "epsilon": 0.2, + "epsilon_high": null, + "delta": null, + "use_vllm": true, + "vllm_mode": null, + "vllm_enable_prefix_caching": true, + "vllm_gpu_memory_utilization": 0.9, + "vllm_tensor_parallel_size": 1, + "vllm_max_model_len": null, + "vllm_enforce_eager": false, + "vllm_limit_mm_per_prompt": null, + "vllm_disable_cascade_attn": false, + "vllm_max_num_seqs": null, + "vllm_mm_processor_cache_gb": null, + "vllm_engine_kwargs": null, + "sleep_level": 0, + "offload_optimizer": false, + "offload_model": false, + "offload_bridge": false, + "vllm_server_base_url": null, + "vllm_server_host": null, + "vllm_server_port": [ + 8000 + ], + "vllm_server_timeout": 240.0, + "vllm_server_group_port": null, + "reward_funcs": [], + "reward_weights": null, + "cosine_min_len_value_wrong": -0.5, + "cosine_max_len_value_wrong": 0.0, + "cosine_min_len_value_correct": 1.0, + "cosine_max_len_value_correct": 0.5, + "cosine_max_len": null, + "repetition_n_grams": 3, + "repetition_max_penalty": -1.0, + "soft_max_length": null, + "soft_cache_length": null, + "dynamic_sample": false, + "max_resample_times": 3, + "overlong_filter": false, + "scale_rewards": "group", + "advantage_estimator": "grpo", + "kl_in_reward": false, + "wandb_log_unique_prompts": null, + "log_completions": false, + "rollout_importance_sampling_mode": null, + "rollout_importance_sampling_threshold": 2.0, + "log_rollout_offpolicy_metrics": false, + "off_policy_sequence_mask_delta": null, + "log_entropy": false, + "top_entropy_quantile": 1.0, + "reward_model": null, + "reward_model_plugin": null, + "sync_ref_model": false, + "ref_model_sync_steps": 512, + "ref_model_mixup_alpha": 0.6, + "async_generate": false, + "move_model_batches": null, + "multi_turn_scheduler": null, + "max_turns": null, + "completion_length_limit_scope": "per_round", + "vllm_server_pass_dataset": false, + "num_iterations": 1, + "check_model": true, + "padded_vocab_size": 151936, + "initialize_embedding": false, + "mlp_padding_free": false, + "load_safetensors": true, + "save_safetensors": true, + "ref_model": null, + "ref_adapters": [], + "merge_lora": true, + "max_shard_size": "5GB", + "train_dataloader_shuffle": true, + "dataloader_pin_memory": true, + "dataloader_persistent_workers": true, + "dataloader_prefetch_factor": 2, + "group_by_length": false, + "architectures": "Qwen3VLMoeForConditionalGeneration", + "llm_architectures": "Qwen3VLMoeForConditionalGeneration", + "max_epochs": 3, + "enable_dft_loss": false, + "enable_channel_loss": false, + "save_strategy": "steps", + "original_max_position_embeddings": null, + "partial_rotary_factor": null, + "use_shared_expert_gate": false, + "report_to": "wandb", + "vit_gradient_checkpointing": true, + "vit_lr": null, + "aligner_lr": null, + "gradient_checkpointing_kwargs": null, + "linear_num_value_heads": null, + "linear_num_key_heads": null, + "linear_key_head_dim": null, + "linear_value_head_dim": null, + "linear_conv_kernel_dim": null, + "layer_types": null, + "apply_wd_to_qk_layernorm": false, + "mrope_interleaved": true, + "micro_batch_size": 2, + "global_batch_size": 16, + "recompute_granularity": "full", + "recompute_method": "uniform", + "recompute_num_layers": 1, + "recompute_modules": [ + "core_attn" + ], + "use_cpu_initialization": false, + "deterministic_mode": false, + "train_iters": null, + "log_interval": 5, + "tensorboard_dir": "/mnt/bn/strategy-mllm-train/user/tanyue/models/ckpts/qwen3vl_30b_highlight_batch1245_v2/runs", + "no_masked_softmax_fusion": false, + "no_bias_dropout_fusion": false, + "no_bias_swiglu_fusion": false, + "no_rope_fusion": false, + "no_gradient_accumulation_fusion": true, + "cross_entropy_loss_fusion": true, + "cross_entropy_fusion_impl": "native", + "calculate_per_token_loss": true, + "use_flash_attn": false, + "attention_backend": "flash", + "optimizer": "adam", + "optimizer_cpu_offload": false, + "optimizer_offload_fraction": 1.0, + "use_precision_aware_optimizer": false, + "main_grads_dtype": "fp32", + "main_params_dtype": "fp32", + "exp_avg_dtype": "fp32", + "exp_avg_sq_dtype": "fp32", + "dataloader_type": "cyclic", + "manual_gc": false, + "manual_gc_interval": 0, + "lr": 1e-05, + "lr_decay_style": "cosine", + "lr_decay_iters": null, + "lr_warmup_iters": 0, + "lr_warmup_fraction": 0.05, + "min_lr": 1e-06, + "weight_decay": 0.1, + "clip_grad": 1.0, + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_eps": 1e-08, + "sgd_momentum": 0.9, + "save": "/mnt/bn/strategy-mllm-train/user/tanyue/models/ckpts/qwen3vl_30b_highlight_batch1245_v2", + "save_interval": 2000, + "save_retain_interval": null, + "no_save_optim": true, + "no_save_rng": true, + "load": null, + "no_load_optim": false, + "no_load_rng": false, + "finetune": true, + "ckpt_format": "torch_dist", + "no_initialization": true, + "auto_detect_ckpt_format": true, + "exit_on_missing_checkpoint": true, + "async_save": false, + "use_persistent_ckpt_worker": false, + "ckpt_fully_parallel_load": false, + "ckpt_assume_constant_structure": false, + "distributed_backend": "nccl", + "local_rank": 0, + "use_distributed_optimizer": true, + "tensor_model_parallel_size": 4, + "pipeline_model_parallel_size": 1, + "decoder_first_pipeline_num_layers": null, + "decoder_last_pipeline_num_layers": null, + "account_for_embedding_in_pipeline_split": false, + "account_for_loss_in_pipeline_split": false, + "sequence_parallel": true, + "context_parallel_size": 1, + "tp_comm_overlap": false, + "overlap_grad_reduce": false, + "overlap_param_gather": false, + "distributed_timeout_minutes": 300000, + "num_layers_per_virtual_pipeline_stage": null, + "num_virtual_stages_per_pipeline_rank": null, + "microbatch_group_size_per_virtual_pipeline_stage": null, + "pipeline_model_parallel_layout": null, + "num_layers": 48, + "hidden_size": 2048, + "ffn_hidden_size": null, + "num_attention_heads": 32, + "group_query_attention": true, + "num_query_groups": 4, + "softmax_type": "vanilla", + "window_size": null, + "window_attn_skip_freq": null, + "max_position_embeddings": 262144, + "position_embedding_type": "mrope", + "mrope_section": [ + 24, + 20, + 20 + ], + "rotary_base": 5000000, + "rotary_percent": 1.0, + "rotary_interleaved": false, + "normalization": "RMSNorm", + "norm_epsilon": 1e-06, + "swiglu": true, + "quick_geglu": false, + "activation_func_clamp_value": null, + "glu_linear_offset": 0.0, + "untie_embeddings_and_output_weights": true, + "disable_bias_linear": true, + "add_qkv_bias": false, + "attention_dropout": 0.0, + "hidden_dropout": 0.0, + "kv_channels": 128, + "qk_layernorm": true, + "qk_l2_norm": null, + "no_rope_freq": null, + "moe_apply_probs_on_input": null, + "transformer_impl": "transformer_engine", + "num_experts": 128, + "moe_layer_freq": 1, + "moe_ffn_hidden_size": 768, + "moe_shared_expert_intermediate_size": null, + "moe_router_topk": 8, + "moe_router_num_groups": null, + "moe_router_group_topk": null, + "moe_router_pre_softmax": false, + "moe_router_dtype": "fp32", + "moe_router_score_function": "softmax", + "moe_router_bias_update_rate": null, + "moe_router_enable_expert_bias": false, + "moe_router_topk_scaling_factor": null, + "moe_router_load_balancing_type": "aux_loss", + "expert_model_parallel_size": 8, + "expert_tensor_parallel_size": 1, + "moe_token_dispatcher_type": null, + "moe_enable_deepep": false, + "moe_grouped_gemm": true, + "moe_permute_fusion": true, + "moe_aux_loss_coeff": 1e-06, + "moe_z_loss_coeff": null, + "moe_shared_expert_overlap": true, + "moe_layer_recompute": false, + "moe_expert_capacity_factor": 2.0, + "moe_pad_expert_input_to_capacity": false, + "moe_token_drop_policy": null, + "multi_latent_attention": false, + "q_lora_rank": null, + "kv_lora_rank": 32, + "qk_head_dim": 128, + "qk_pos_emb_head_dim": 64, + "mtp_num_layers": null, + "mtp_loss_scaling_factor": 0.1, + "fp8_format": null, + "fp8_recipe": "delayed", + "fp8_amax_history_len": 1024, + "fp8_amax_compute_algo": "max", + "fp8_param_gather": false, + "fp16": false, + "bf16": true, + "apply_query_key_layer_scaling": false, + "attention_softmax_in_fp32": true, + "log_params_norm": false, + "log_throughput": false, + "tensorboard_log_interval": 1, + "tensorboard_queue_size": 50, + "log_timers_to_tensorboard": true, + "no_log_learning_rate_to_tensorboard": false, + "log_validation_ppl_to_tensorboard": true, + "log_memory_to_tensorboard": true, + "logging_level": null, + "wandb_project": "megatron-swift", + "wandb_exp_name": "/mnt/bn/strategy-mllm-train/user/tanyue/models/ckpts/qwen3vl_30b_highlight_batch1245_v2", + "wandb_save_dir": null, + "eval_iters": -1, + "eval_interval": 2000, + "seq_length": 8192, + "num_workers": 8, + "no_data_sharding": false, + "megatron_extra_kwargs": {}, + "add_version": false, + "rank": 0, + "global_world_size": 8, + "local_world_size": 8, + "model_suffix": "Qwen3-VL-30B-A3B-Instruct", + "model_info": "ModelInfo(model_type='qwen3_moe_vl', model_dir='/opt/tiger/tanyue/highlight_tools/checkpoints/Qwen3-VL-30B-A3B-Instruct', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default'}, is_moe_model=True, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)", + "model_meta": "ModelMeta(model_type='qwen3_moe_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_vl', get_function=, model_arch=MultiModelKeys(arch_name='qwen3_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen3VLMoeForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])", + "model_dir": "/opt/tiger/tanyue/highlight_tools/checkpoints/Qwen3-VL-30B-A3B-Instruct", + "_val_dataset_exists": [], + "hub": "", + "megatron_model_meta": "MegatronModelMeta(megatron_model_type='qwen3_vl', model_types=['qwen3_vl', 'qwen3_moe_vl'], is_multimodal=True, bridge_cls=, model_cls=, get_transformer_layer_spec=None, model_provider=, visual_cls=, get_mtp_block_spec=None, extra_args_provider=None)", + "extra_args": { + "model_dir": "/opt/tiger/tanyue/highlight_tools/checkpoints/Qwen3-VL-30B-A3B-Instruct", + "is_multimodal": true, + "hf_model_type": "qwen3_moe_vl", + "use_ray": false, + "ray_exp_name": null, + "device_groups": null, + "model": "checkpoints/Qwen3-VL-30B-A3B-Instruct", + "model_type": "qwen3_moe_vl", + "model_revision": null, + "task_type": "causal_lm", + "torch_dtype": "bfloat16", + "attn_impl": null, + "new_special_tokens": [], + "num_labels": null, + "problem_type": null, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_type": "default" + }, + "device_map": null, + "max_memory": {}, + "max_model_len": null, + "local_repo_path": null, + "init_strategy": null, + "template": "qwen3_vl", + "system": null, + "max_length": 8192, + "truncation_strategy": "delete", + "max_pixels": null, + "agent_template": null, + "norm_bbox": null, + "use_chat_template": true, + "padding_side": "right", + "padding_free": true, + "sequence_parallel_size": 1, + "template_backend": "swift", + "response_prefix": null, + "enable_thinking": null, + "add_non_thinking_prefix": true, + "dataset": [ + "highlight_batch1", + "highlight_batch2", + "highlight_batch4_part1", + "highlight_batch4_part2", + "highlight_batch4_part3", + "highlight_batch5_part1", + "highlight_batch5_part2", + "highlight_batch5_part3" + ], + "val_dataset": [], + "cached_dataset": [], + "cached_val_dataset": [], + "split_dataset_ratio": 0.0, + "data_seed": 42, + "dataset_num_proc": 8, + "load_from_cache_file": false, + "dataset_shuffle": true, + "val_dataset_shuffle": false, + "streaming": false, + "interleave_prob": null, + "stopping_strategy": "first_exhausted", + "shuffle_buffer_size": 1000, + "download_mode": "reuse_dataset_if_exists", + "columns": {}, + "strict": false, + "remove_unused_columns": true, + "model_name": null, + "model_author": null, + "custom_dataset_info": [], + "quant_method": null, + "quant_bits": null, + "hqq_axis": null, + "bnb_4bit_compute_dtype": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "max_new_tokens": null, + "temperature": 0.9, + "top_k": 50, + "top_p": 0.9, + "repetition_penalty": 1.0, + "num_beams": 1, + "stream": false, + "stop_words": [], + "logprobs": false, + "top_logprobs": null, + "structured_outputs_regex": null, + "ckpt_dir": null, + "lora_modules": [], + "tuner_backend": "peft", + "train_type": "lora", + "adapters": [], + "external_plugins": [], + "model_kwargs": {}, + "load_args": false, + "load_data_args": false, + "packing": false, + "packing_length": null, + "packing_num_proc": 1, + "lazy_tokenize": true, + "custom_register_path": [ + "ms-swift/custom_video_dataset_base.py" + ], + "use_hf": false, + "hub_token": null, + "ddp_timeout": 18000000, + "ddp_backend": null, + "ignore_args_error": false, + "use_swift_lora": false, + "freeze_llm": false, + "freeze_vit": true, + "freeze_aligner": true, + "freeze_parameters": [], + "freeze_parameters_regex": null, + "freeze_parameters_ratio": 0.0, + "trainable_parameters": [], + "trainable_parameters_regex": null, + "adapter_load": null, + "target_modules": [ + "all-linear" + ], + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias": "none", + "lora_dtype": null, + "use_rslora": false, + "rlhf_type": null, + "ref_load": null, + "ref_adapter_load": null, + "beta": null, + "rpo_alpha": null, + "reference_free": false, + "label_smoothing": 0.0, + "f_divergence_type": "reverse_kl", + "loss_type": null, + "desirable_weight": 1.0, + "undesirable_weight": 1.0, + "calculate_KL": null, + "center_rewards_coefficient": null, + "teacher_model": null, + "teacher_model_type": null, + "teacher_model_revision": null, + "lmbda": 0.5, + "seq_kd": false, + "offload_teacher_model": false, + "sft_alpha": 0.0, + "generation_batch_size": null, + "steps_per_generation": null, + "num_generations": 8, + "num_generations_eval": null, + "max_completion_length": 512, + "importance_sampling_level": "token", + "tau_pos": 1.0, + "tau_neg": 1.05, + "epsilon": 0.2, + "epsilon_high": null, + "delta": null, + "use_vllm": true, + "vllm_mode": null, + "vllm_enable_prefix_caching": true, + "vllm_gpu_memory_utilization": 0.9, + "vllm_tensor_parallel_size": 1, + "vllm_max_model_len": null, + "vllm_enforce_eager": false, + "vllm_limit_mm_per_prompt": null, + "vllm_disable_cascade_attn": false, + "vllm_max_num_seqs": null, + "vllm_mm_processor_cache_gb": null, + "vllm_engine_kwargs": null, + "sleep_level": 0, + "offload_optimizer": false, + "offload_model": false, + "offload_bridge": false, + "vllm_server_base_url": null, + "vllm_server_host": null, + "vllm_server_port": [ + 8000 + ], + "vllm_server_timeout": 240.0, + "vllm_server_group_port": null, + "reward_funcs": [], + "reward_weights": null, + "cosine_min_len_value_wrong": -0.5, + "cosine_max_len_value_wrong": 0.0, + "cosine_min_len_value_correct": 1.0, + "cosine_max_len_value_correct": 0.5, + "cosine_max_len": null, + "repetition_n_grams": 3, + "repetition_max_penalty": -1.0, + "soft_max_length": null, + "soft_cache_length": null, + "dynamic_sample": false, + "max_resample_times": 3, + "overlong_filter": false, + "scale_rewards": "group", + "advantage_estimator": "grpo", + "kl_in_reward": false, + "wandb_log_unique_prompts": null, + "log_completions": false, + "rollout_importance_sampling_mode": null, + "rollout_importance_sampling_threshold": 2.0, + "log_rollout_offpolicy_metrics": false, + "off_policy_sequence_mask_delta": null, + "log_entropy": false, + "top_entropy_quantile": 1.0, + "reward_model": null, + "reward_model_plugin": null, + "sync_ref_model": false, + "ref_model_sync_steps": 512, + "ref_model_mixup_alpha": 0.6, + "async_generate": false, + "move_model_batches": null, + "multi_turn_scheduler": null, + "max_turns": null, + "completion_length_limit_scope": "per_round", + "vllm_server_pass_dataset": false, + "num_iterations": 1, + "check_model": true, + "padded_vocab_size": 151936, + "initialize_embedding": false, + "mlp_padding_free": false, + "load_safetensors": true, + "save_safetensors": true, + "ref_model": null, + "ref_adapters": [], + "merge_lora": true, + "max_shard_size": "5GB", + "train_dataloader_shuffle": true, + "dataloader_pin_memory": true, + "dataloader_persistent_workers": true, + "dataloader_prefetch_factor": 2, + "group_by_length": false, + "architectures": "Qwen3VLMoeForConditionalGeneration", + "llm_architectures": "Qwen3VLMoeForConditionalGeneration", + "max_epochs": 3, + "enable_dft_loss": false, + "enable_channel_loss": false, + "save_strategy": "steps", + "original_max_position_embeddings": null, + "partial_rotary_factor": null, + "use_shared_expert_gate": false, + "report_to": "wandb", + "vit_gradient_checkpointing": true, + "vit_lr": null, + "aligner_lr": null, + "gradient_checkpointing_kwargs": null, + "linear_num_value_heads": null, + "linear_num_key_heads": null, + "linear_key_head_dim": null, + "linear_value_head_dim": null, + "linear_conv_kernel_dim": null, + "layer_types": null, + "apply_wd_to_qk_layernorm": false, + "mrope_interleaved": true, + "add_version": false + } +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/chat_template.jinja b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/config.json b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/config.json new file mode 100644 index 0000000000000000000000000000000000000000..b0a6ccdb1e5f9ddc61485e04a3a7766b46ee855c --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/config.json @@ -0,0 +1,76 @@ +{ + "architectures": [ + "Qwen3VLMoeForConditionalGeneration" + ], + "dtype": "bfloat16", + "hidden_size": 2048, + "image_token_id": 151655, + "model_type": "qwen3_vl_moe", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "decoder_sparse_step": 1, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "max_position_embeddings": 262144, + "mlp_only_layers": [], + "model_type": "qwen3_vl_moe_text", + "moe_intermediate_size": 768, + "norm_topk_prob": true, + "num_attention_heads": 32, + "num_experts": 128, + "num_experts_per_tok": 8, + "num_hidden_layers": 48, + "num_key_value_heads": 4, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_type": "default" + }, + "rope_theta": 5000000, + "router_aux_loss_coef": 0.001, + "use_cache": true, + "vocab_size": 151936 + }, + "tie_word_embeddings": false, + "transformers_version": "4.57.6", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 8, + 16, + 24 + ], + "depth": 27, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4304, + "model_type": "qwen3_vl_moe", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2048, + "pad_token_id": 151643, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652, + "vocab_size": 151936 +} diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/iter_0008583/common.pt b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/iter_0008583/common.pt new file mode 100644 index 0000000000000000000000000000000000000000..d7681770fab705d4a142ed201b28b8a562b793a6 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/iter_0008583/common.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a9a0a92fd63793bc30a31d5d37eb6d847a02a241ea9c27074a915e29ed2ea5 +size 28327 diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/latest_checkpointed_iteration.txt b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/latest_checkpointed_iteration.txt new file mode 100644 index 0000000000000000000000000000000000000000..be193ca94ce521b4b1667a2a0e0a212c2b2e44b3 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/latest_checkpointed_iteration.txt @@ -0,0 +1 @@ +8583 \ No newline at end of file diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/model.safetensors.index.json b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..8e4a527923fdd0d0160b588bffcf97547fbb6643 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/model.safetensors.index.json @@ -0,0 +1,889 @@ +{ + "metadata": { + "total_size": 62141508064 + }, + "weight_map": { + "model.language_model.embed_tokens.weight": "model-00001-of-00013.safetensors", + "model.visual.patch_embed.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.patch_embed.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.pos_embed.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00013.safetensors", + "model.visual.merger.norm.bias": "model-00001-of-00013.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.mlp.gate.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.mlp.experts.down_proj": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.mlp.gate.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.mlp.experts.down_proj": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.mlp.gate.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.2.mlp.experts.down_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.mlp.gate.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.mlp.experts.down_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.mlp.gate.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.mlp.experts.down_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.mlp.gate.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.mlp.experts.down_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.mlp.gate.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.6.mlp.experts.down_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.mlp.gate.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.mlp.experts.down_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.mlp.gate.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.mlp.experts.down_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.mlp.gate.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.mlp.experts.down_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.mlp.gate.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.10.mlp.experts.down_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.mlp.gate.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.mlp.experts.down_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.mlp.gate.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.mlp.experts.down_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.mlp.gate.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.mlp.experts.down_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.mlp.gate.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.14.mlp.experts.down_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.mlp.gate.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.mlp.experts.down_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.mlp.gate.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.mlp.experts.down_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.mlp.gate.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.mlp.experts.down_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.mlp.gate.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.18.mlp.experts.down_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.mlp.gate.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.mlp.experts.down_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.mlp.gate.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.mlp.experts.down_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.mlp.gate.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.mlp.experts.down_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.mlp.gate.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.22.mlp.experts.down_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.mlp.gate.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.mlp.experts.down_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.mlp.gate.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.mlp.experts.down_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.mlp.gate.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.mlp.experts.down_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.mlp.gate.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.26.mlp.experts.down_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.mlp.gate.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.mlp.experts.down_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.mlp.gate.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.mlp.experts.down_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.mlp.gate.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.mlp.experts.down_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.mlp.gate.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.30.mlp.experts.down_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.mlp.gate.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.mlp.experts.down_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.mlp.gate.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.mlp.experts.down_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.mlp.gate.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.mlp.experts.down_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.mlp.gate.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.34.mlp.experts.down_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.mlp.gate.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.mlp.experts.down_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.mlp.gate.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.mlp.experts.down_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.mlp.gate.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.mlp.experts.down_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.mlp.gate.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.38.mlp.experts.down_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.38.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.mlp.gate.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.mlp.experts.down_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.mlp.gate.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.mlp.experts.down_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.mlp.gate.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.mlp.experts.down_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.mlp.gate.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.42.mlp.experts.down_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.42.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.mlp.gate.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.mlp.experts.down_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.mlp.gate.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.mlp.experts.down_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.mlp.gate.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.mlp.experts.down_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.mlp.gate.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.mlp.experts.gate_up_proj": "model-00013-of-00013.safetensors", + "model.language_model.layers.46.mlp.experts.down_proj": "model-00013-of-00013.safetensors", + "model.language_model.layers.46.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.self_attn.q_norm.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.self_attn.k_norm.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.input_layernorm.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.mlp.gate.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.mlp.experts.gate_up_proj": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.mlp.experts.down_proj": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", + "lm_head.weight": "model-00013-of-00013.safetensors", + "model.language_model.norm.weight": "model-00013-of-00013.safetensors" + } +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/preprocessor_config.json b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..2ea84a437d448ff71b08df68fdd949d5cc4ebb64 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/preprocessor_config.json @@ -0,0 +1,21 @@ +{ + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "patch_size": 16, + "temporal_patch_size": 2, + "merge_size": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "processor_class": "Qwen3VLProcessor", + "image_processor_type": "Qwen2VLImageProcessorFast" +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/special_tokens_map.json b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/tokenizer_config.json b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/video_preprocessor_config.json b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/video_preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e32b1d90356f74457edbfca27aa1e121dab7cdc7 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1245_v2/video_preprocessor_config.json @@ -0,0 +1,41 @@ +{ + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" +} diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/args.json b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/args.json new file mode 100644 index 0000000000000000000000000000000000000000..483c814a0d63e8a1b3d0362c9c04f3e4d85798c4 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/args.json @@ -0,0 +1,704 @@ +{ + "use_ray": false, + "ray_exp_name": null, + "device_groups": null, + "model": "checkpoints/Qwen3-VL-30B-A3B-Instruct", + "model_type": "qwen3_moe_vl", + "model_revision": null, + "task_type": "causal_lm", + "torch_dtype": "bfloat16", + "attn_impl": null, + "new_special_tokens": [], + "num_labels": null, + "problem_type": null, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_type": "default" + }, + "device_map": null, + "max_memory": {}, + "max_model_len": null, + "local_repo_path": null, + "init_strategy": null, + "template": "qwen3_vl", + "system": null, + "max_length": 8192, + "truncation_strategy": "delete", + "max_pixels": null, + "agent_template": null, + "norm_bbox": null, + "use_chat_template": true, + "padding_side": "right", + "padding_free": true, + "loss_scale": "default", + "sequence_parallel_size": 1, + "template_backend": "swift", + "response_prefix": null, + "enable_thinking": null, + "add_non_thinking_prefix": true, + "dataset": [ + "highlight_batch1" + ], + "val_dataset": [], + "cached_dataset": [], + "cached_val_dataset": [], + "split_dataset_ratio": 0.0, + "data_seed": 42, + "dataset_num_proc": 8, + "load_from_cache_file": false, + "dataset_shuffle": true, + "val_dataset_shuffle": false, + "streaming": false, + "interleave_prob": null, + "stopping_strategy": "first_exhausted", + "shuffle_buffer_size": 1000, + "download_mode": "reuse_dataset_if_exists", + "columns": {}, + "strict": false, + "remove_unused_columns": true, + "model_name": null, + "model_author": null, + "custom_dataset_info": [], + "quant_method": null, + "quant_bits": null, + "hqq_axis": null, + "bnb_4bit_compute_dtype": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "max_new_tokens": null, + "temperature": 0.9, + "top_k": 50, + "top_p": 0.9, + "repetition_penalty": 1.0, + "num_beams": 1, + "stream": false, + "stop_words": [], + "logprobs": false, + "top_logprobs": null, + "structured_outputs_regex": null, + "ckpt_dir": null, + "lora_modules": [], + "tuner_backend": "peft", + "train_type": "lora", + "adapters": [], + "external_plugins": [], + "seed": 42, + "model_kwargs": {}, + "load_args": false, + "load_data_args": false, + "packing": false, + "packing_length": null, + "packing_num_proc": 1, + "lazy_tokenize": true, + "custom_register_path": [ + "ms-swift/custom_video_dataset_base.py" + ], + "use_hf": false, + "hub_token": null, + "ddp_timeout": 18000000, + "ddp_backend": null, + "ignore_args_error": false, + "use_swift_lora": false, + "freeze_llm": false, + "freeze_vit": true, + "freeze_aligner": true, + "freeze_parameters": [], + "freeze_parameters_regex": null, + "freeze_parameters_ratio": 0.0, + "trainable_parameters": [], + "trainable_parameters_regex": null, + "adapter_load": null, + "target_modules": [ + "all-linear" + ], + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias": "none", + "lora_dtype": null, + "use_rslora": false, + "rlhf_type": null, + "ref_load": null, + "ref_adapter_load": null, + "beta": null, + "rpo_alpha": null, + "reference_free": false, + "label_smoothing": 0.0, + "f_divergence_type": "reverse_kl", + "loss_type": null, + "desirable_weight": 1.0, + "undesirable_weight": 1.0, + "calculate_KL": null, + "center_rewards_coefficient": null, + "teacher_model": null, + "teacher_model_type": null, + "teacher_model_revision": null, + "lmbda": 0.5, + "seq_kd": false, + "offload_teacher_model": false, + "sft_alpha": 0.0, + "generation_batch_size": null, + "steps_per_generation": null, + "num_generations": 8, + "num_generations_eval": null, + "max_completion_length": 512, + "importance_sampling_level": "token", + "tau_pos": 1.0, + "tau_neg": 1.05, + "epsilon": 0.2, + "epsilon_high": null, + "delta": null, + "use_vllm": true, + "vllm_mode": null, + "vllm_enable_prefix_caching": true, + "vllm_gpu_memory_utilization": 0.9, + "vllm_tensor_parallel_size": 1, + "vllm_max_model_len": null, + "vllm_enforce_eager": false, + "vllm_limit_mm_per_prompt": null, + "vllm_disable_cascade_attn": false, + "vllm_max_num_seqs": null, + "vllm_mm_processor_cache_gb": null, + "vllm_engine_kwargs": null, + "sleep_level": 0, + "offload_optimizer": false, + "offload_model": false, + "offload_bridge": false, + "vllm_server_base_url": null, + "vllm_server_host": null, + "vllm_server_port": [ + 8000 + ], + "vllm_server_timeout": 240.0, + "vllm_server_group_port": null, + "reward_funcs": [], + "reward_weights": null, + "cosine_min_len_value_wrong": -0.5, + "cosine_max_len_value_wrong": 0.0, + "cosine_min_len_value_correct": 1.0, + "cosine_max_len_value_correct": 0.5, + "cosine_max_len": null, + "repetition_n_grams": 3, + "repetition_max_penalty": -1.0, + "soft_max_length": null, + "soft_cache_length": null, + "dynamic_sample": false, + "max_resample_times": 3, + "overlong_filter": false, + "scale_rewards": "group", + "advantage_estimator": "grpo", + "kl_in_reward": false, + "wandb_log_unique_prompts": null, + "log_completions": false, + "rollout_importance_sampling_mode": null, + "rollout_importance_sampling_threshold": 2.0, + "log_rollout_offpolicy_metrics": false, + "off_policy_sequence_mask_delta": null, + "log_entropy": false, + "top_entropy_quantile": 1.0, + "reward_model": null, + "reward_model_plugin": null, + "sync_ref_model": false, + "ref_model_sync_steps": 512, + "ref_model_mixup_alpha": 0.6, + "async_generate": false, + "move_model_batches": null, + "multi_turn_scheduler": null, + "max_turns": null, + "completion_length_limit_scope": "per_round", + "vllm_server_pass_dataset": false, + "num_iterations": 1, + "check_model": true, + "padded_vocab_size": 151936, + "initialize_embedding": false, + "mlp_padding_free": false, + "load_safetensors": true, + "save_safetensors": true, + "ref_model": null, + "ref_adapters": [], + "merge_lora": true, + "max_shard_size": "5GB", + "train_dataloader_shuffle": true, + "dataloader_pin_memory": true, + "dataloader_persistent_workers": true, + "dataloader_prefetch_factor": 2, + "group_by_length": false, + "architectures": "Qwen3VLMoeForConditionalGeneration", + "llm_architectures": "Qwen3VLMoeForConditionalGeneration", + "max_epochs": 4, + "enable_dft_loss": false, + "enable_channel_loss": false, + "save_strategy": "steps", + "original_max_position_embeddings": null, + "partial_rotary_factor": null, + "use_shared_expert_gate": false, + "report_to": "wandb", + "vit_gradient_checkpointing": true, + "vit_lr": null, + "aligner_lr": null, + "gradient_checkpointing_kwargs": null, + "linear_num_value_heads": null, + "linear_num_key_heads": null, + "linear_key_head_dim": null, + "linear_value_head_dim": null, + "linear_conv_kernel_dim": null, + "layer_types": null, + "apply_wd_to_qk_layernorm": false, + "mrope_interleaved": true, + "micro_batch_size": 2, + "global_batch_size": 16, + "recompute_granularity": "full", + "recompute_method": "uniform", + "recompute_num_layers": 1, + "recompute_modules": [ + "core_attn" + ], + "use_cpu_initialization": false, + "deterministic_mode": false, + "train_iters": null, + "log_interval": 5, + "tensorboard_dir": "/mnt/bn/strategy-mllm-train/user/tanyue/models/ckpts/qwen3vl_30b_highlight_batch1_epoch4_lora/runs", + "no_masked_softmax_fusion": false, + "no_bias_dropout_fusion": false, + "no_bias_swiglu_fusion": false, + "no_rope_fusion": false, + "no_gradient_accumulation_fusion": true, + "cross_entropy_loss_fusion": true, + "cross_entropy_fusion_impl": "native", + "calculate_per_token_loss": true, + "use_flash_attn": false, + "attention_backend": "flash", + "optimizer": "adam", + "optimizer_cpu_offload": false, + "optimizer_offload_fraction": 1.0, + "use_precision_aware_optimizer": false, + "main_grads_dtype": "fp32", + "main_params_dtype": "fp32", + "exp_avg_dtype": "fp32", + "exp_avg_sq_dtype": "fp32", + "dataloader_type": "cyclic", + "manual_gc": false, + "manual_gc_interval": 0, + "lr": 1e-05, + "lr_decay_style": "cosine", + "lr_decay_iters": null, + "lr_warmup_iters": 0, + "lr_warmup_fraction": 0.05, + "min_lr": 1e-06, + "weight_decay": 0.1, + "clip_grad": 1.0, + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_eps": 1e-08, + "sgd_momentum": 0.9, + "save": "/mnt/bn/strategy-mllm-train/user/tanyue/models/ckpts/qwen3vl_30b_highlight_batch1_epoch4_lora", + "save_interval": 2000, + "save_retain_interval": null, + "no_save_optim": true, + "no_save_rng": true, + "load": null, + "no_load_optim": false, + "no_load_rng": false, + "finetune": true, + "ckpt_format": "torch_dist", + "no_initialization": true, + "auto_detect_ckpt_format": true, + "exit_on_missing_checkpoint": true, + "async_save": false, + "use_persistent_ckpt_worker": false, + "ckpt_fully_parallel_load": false, + "ckpt_assume_constant_structure": false, + "distributed_backend": "nccl", + "local_rank": 0, + "use_distributed_optimizer": true, + "tensor_model_parallel_size": 4, + "pipeline_model_parallel_size": 1, + "decoder_first_pipeline_num_layers": null, + "decoder_last_pipeline_num_layers": null, + "account_for_embedding_in_pipeline_split": false, + "account_for_loss_in_pipeline_split": false, + "sequence_parallel": true, + "context_parallel_size": 1, + "tp_comm_overlap": false, + "overlap_grad_reduce": false, + "overlap_param_gather": false, + "distributed_timeout_minutes": 300000, + "num_layers_per_virtual_pipeline_stage": null, + "num_virtual_stages_per_pipeline_rank": null, + "microbatch_group_size_per_virtual_pipeline_stage": null, + "pipeline_model_parallel_layout": null, + "num_layers": 48, + "hidden_size": 2048, + "ffn_hidden_size": null, + "num_attention_heads": 32, + "group_query_attention": true, + "num_query_groups": 4, + "softmax_type": "vanilla", + "window_size": null, + "window_attn_skip_freq": null, + "max_position_embeddings": 262144, + "position_embedding_type": "mrope", + "mrope_section": [ + 24, + 20, + 20 + ], + "rotary_base": 5000000, + "rotary_percent": 1.0, + "rotary_interleaved": false, + "normalization": "RMSNorm", + "norm_epsilon": 1e-06, + "swiglu": true, + "quick_geglu": false, + "activation_func_clamp_value": null, + "glu_linear_offset": 0.0, + "untie_embeddings_and_output_weights": true, + "disable_bias_linear": true, + "add_qkv_bias": false, + "attention_dropout": 0.0, + "hidden_dropout": 0.0, + "kv_channels": 128, + "qk_layernorm": true, + "qk_l2_norm": null, + "no_rope_freq": null, + "moe_apply_probs_on_input": null, + "transformer_impl": "transformer_engine", + "num_experts": 128, + "moe_layer_freq": 1, + "moe_ffn_hidden_size": 768, + "moe_shared_expert_intermediate_size": null, + "moe_router_topk": 8, + "moe_router_num_groups": null, + "moe_router_group_topk": null, + "moe_router_pre_softmax": false, + "moe_router_dtype": "fp32", + "moe_router_score_function": "softmax", + "moe_router_bias_update_rate": null, + "moe_router_enable_expert_bias": false, + "moe_router_topk_scaling_factor": null, + "moe_router_load_balancing_type": "aux_loss", + "expert_model_parallel_size": 8, + "expert_tensor_parallel_size": 1, + "moe_token_dispatcher_type": null, + "moe_enable_deepep": false, + "moe_grouped_gemm": true, + "moe_permute_fusion": true, + "moe_aux_loss_coeff": 1e-06, + "moe_z_loss_coeff": null, + "moe_shared_expert_overlap": true, + "moe_layer_recompute": false, + "moe_expert_capacity_factor": 2.0, + "moe_pad_expert_input_to_capacity": false, + "moe_token_drop_policy": null, + "multi_latent_attention": false, + "q_lora_rank": null, + "kv_lora_rank": 32, + "qk_head_dim": 128, + "qk_pos_emb_head_dim": 64, + "mtp_num_layers": null, + "mtp_loss_scaling_factor": 0.1, + "fp8_format": null, + "fp8_recipe": "delayed", + "fp8_amax_history_len": 1024, + "fp8_amax_compute_algo": "max", + "fp8_param_gather": false, + "fp16": false, + "bf16": true, + "apply_query_key_layer_scaling": false, + "attention_softmax_in_fp32": true, + "log_params_norm": false, + "log_throughput": false, + "tensorboard_log_interval": 1, + "tensorboard_queue_size": 50, + "log_timers_to_tensorboard": true, + "no_log_learning_rate_to_tensorboard": false, + "log_validation_ppl_to_tensorboard": true, + "log_memory_to_tensorboard": true, + "logging_level": null, + "wandb_project": "megatron-swift", + "wandb_exp_name": "/mnt/bn/strategy-mllm-train/user/tanyue/models/ckpts/qwen3vl_30b_highlight_batch1_epoch4_lora", + "wandb_save_dir": null, + "eval_iters": -1, + "eval_interval": 2000, + "seq_length": 8192, + "num_workers": 8, + "no_data_sharding": false, + "megatron_extra_kwargs": {}, + "add_version": false, + "rank": 0, + "global_world_size": 8, + "local_world_size": 8, + "model_suffix": "Qwen3-VL-30B-A3B-Instruct", + "model_info": "ModelInfo(model_type='qwen3_moe_vl', model_dir='/opt/tiger/tanyue/highlight_tools/checkpoints/Qwen3-VL-30B-A3B-Instruct', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default'}, is_moe_model=True, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)", + "model_meta": "ModelMeta(model_type='qwen3_moe_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_vl', get_function=, model_arch=MultiModelKeys(arch_name='qwen3_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen3VLMoeForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])", + "model_dir": "/opt/tiger/tanyue/highlight_tools/checkpoints/Qwen3-VL-30B-A3B-Instruct", + "_val_dataset_exists": [], + "hub": "", + "megatron_model_meta": "MegatronModelMeta(megatron_model_type='qwen3_vl', model_types=['qwen3_vl', 'qwen3_moe_vl'], is_multimodal=True, bridge_cls=, model_cls=, get_transformer_layer_spec=None, model_provider=, visual_cls=, get_mtp_block_spec=None, extra_args_provider=None)", + "extra_args": { + "model_dir": "/opt/tiger/tanyue/highlight_tools/checkpoints/Qwen3-VL-30B-A3B-Instruct", + "is_multimodal": true, + "hf_model_type": "qwen3_moe_vl", + "use_ray": false, + "ray_exp_name": null, + "device_groups": null, + "model": "checkpoints/Qwen3-VL-30B-A3B-Instruct", + "model_type": "qwen3_moe_vl", + "model_revision": null, + "task_type": "causal_lm", + "torch_dtype": "bfloat16", + "attn_impl": null, + "new_special_tokens": [], + "num_labels": null, + "problem_type": null, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_type": "default" + }, + "device_map": null, + "max_memory": {}, + "max_model_len": null, + "local_repo_path": null, + "init_strategy": null, + "template": "qwen3_vl", + "system": null, + "max_length": 8192, + "truncation_strategy": "delete", + "max_pixels": null, + "agent_template": null, + "norm_bbox": null, + "use_chat_template": true, + "padding_side": "right", + "padding_free": true, + "sequence_parallel_size": 1, + "template_backend": "swift", + "response_prefix": null, + "enable_thinking": null, + "add_non_thinking_prefix": true, + "dataset": [ + "highlight_batch1" + ], + "val_dataset": [], + "cached_dataset": [], + "cached_val_dataset": [], + "split_dataset_ratio": 0.0, + "data_seed": 42, + "dataset_num_proc": 8, + "load_from_cache_file": false, + "dataset_shuffle": true, + "val_dataset_shuffle": false, + "streaming": false, + "interleave_prob": null, + "stopping_strategy": "first_exhausted", + "shuffle_buffer_size": 1000, + "download_mode": "reuse_dataset_if_exists", + "columns": {}, + "strict": false, + "remove_unused_columns": true, + "model_name": null, + "model_author": null, + "custom_dataset_info": [], + "quant_method": null, + "quant_bits": null, + "hqq_axis": null, + "bnb_4bit_compute_dtype": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "max_new_tokens": null, + "temperature": 0.9, + "top_k": 50, + "top_p": 0.9, + "repetition_penalty": 1.0, + "num_beams": 1, + "stream": false, + "stop_words": [], + "logprobs": false, + "top_logprobs": null, + "structured_outputs_regex": null, + "ckpt_dir": null, + "lora_modules": [], + "tuner_backend": "peft", + "train_type": "lora", + "adapters": [], + "external_plugins": [], + "model_kwargs": {}, + "load_args": false, + "load_data_args": false, + "packing": false, + "packing_length": null, + "packing_num_proc": 1, + "lazy_tokenize": true, + "custom_register_path": [ + "ms-swift/custom_video_dataset_base.py" + ], + "use_hf": false, + "hub_token": null, + "ddp_timeout": 18000000, + "ddp_backend": null, + "ignore_args_error": false, + "use_swift_lora": false, + "freeze_llm": false, + "freeze_vit": true, + "freeze_aligner": true, + "freeze_parameters": [], + "freeze_parameters_regex": null, + "freeze_parameters_ratio": 0.0, + "trainable_parameters": [], + "trainable_parameters_regex": null, + "adapter_load": null, + "target_modules": [ + "all-linear" + ], + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias": "none", + "lora_dtype": null, + "use_rslora": false, + "rlhf_type": null, + "ref_load": null, + "ref_adapter_load": null, + "beta": null, + "rpo_alpha": null, + "reference_free": false, + "label_smoothing": 0.0, + "f_divergence_type": "reverse_kl", + "loss_type": null, + "desirable_weight": 1.0, + "undesirable_weight": 1.0, + "calculate_KL": null, + "center_rewards_coefficient": null, + "teacher_model": null, + "teacher_model_type": null, + "teacher_model_revision": null, + "lmbda": 0.5, + "seq_kd": false, + "offload_teacher_model": false, + "sft_alpha": 0.0, + "generation_batch_size": null, + "steps_per_generation": null, + "num_generations": 8, + "num_generations_eval": null, + "max_completion_length": 512, + "importance_sampling_level": "token", + "tau_pos": 1.0, + "tau_neg": 1.05, + "epsilon": 0.2, + "epsilon_high": null, + "delta": null, + "use_vllm": true, + "vllm_mode": null, + "vllm_enable_prefix_caching": true, + "vllm_gpu_memory_utilization": 0.9, + "vllm_tensor_parallel_size": 1, + "vllm_max_model_len": null, + "vllm_enforce_eager": false, + "vllm_limit_mm_per_prompt": null, + "vllm_disable_cascade_attn": false, + "vllm_max_num_seqs": null, + "vllm_mm_processor_cache_gb": null, + "vllm_engine_kwargs": null, + "sleep_level": 0, + "offload_optimizer": false, + "offload_model": false, + "offload_bridge": false, + "vllm_server_base_url": null, + "vllm_server_host": null, + "vllm_server_port": [ + 8000 + ], + "vllm_server_timeout": 240.0, + "vllm_server_group_port": null, + "reward_funcs": [], + "reward_weights": null, + "cosine_min_len_value_wrong": -0.5, + "cosine_max_len_value_wrong": 0.0, + "cosine_min_len_value_correct": 1.0, + "cosine_max_len_value_correct": 0.5, + "cosine_max_len": null, + "repetition_n_grams": 3, + "repetition_max_penalty": -1.0, + "soft_max_length": null, + "soft_cache_length": null, + "dynamic_sample": false, + "max_resample_times": 3, + "overlong_filter": false, + "scale_rewards": "group", + "advantage_estimator": "grpo", + "kl_in_reward": false, + "wandb_log_unique_prompts": null, + "log_completions": false, + "rollout_importance_sampling_mode": null, + "rollout_importance_sampling_threshold": 2.0, + "log_rollout_offpolicy_metrics": false, + "off_policy_sequence_mask_delta": null, + "log_entropy": false, + "top_entropy_quantile": 1.0, + "reward_model": null, + "reward_model_plugin": null, + "sync_ref_model": false, + "ref_model_sync_steps": 512, + "ref_model_mixup_alpha": 0.6, + "async_generate": false, + "move_model_batches": null, + "multi_turn_scheduler": null, + "max_turns": null, + "completion_length_limit_scope": "per_round", + "vllm_server_pass_dataset": false, + "num_iterations": 1, + "check_model": true, + "padded_vocab_size": 151936, + "initialize_embedding": false, + "mlp_padding_free": false, + "load_safetensors": true, + "save_safetensors": true, + "ref_model": null, + "ref_adapters": [], + "merge_lora": true, + "max_shard_size": "5GB", + "train_dataloader_shuffle": true, + "dataloader_pin_memory": true, + "dataloader_persistent_workers": true, + "dataloader_prefetch_factor": 2, + "group_by_length": false, + "architectures": "Qwen3VLMoeForConditionalGeneration", + "llm_architectures": "Qwen3VLMoeForConditionalGeneration", + "max_epochs": 4, + "enable_dft_loss": false, + "enable_channel_loss": false, + "save_strategy": "steps", + "original_max_position_embeddings": null, + "partial_rotary_factor": null, + "use_shared_expert_gate": false, + "report_to": "wandb", + "vit_gradient_checkpointing": true, + "vit_lr": null, + "aligner_lr": null, + "gradient_checkpointing_kwargs": null, + "linear_num_value_heads": null, + "linear_num_key_heads": null, + "linear_key_head_dim": null, + "linear_value_head_dim": null, + "linear_conv_kernel_dim": null, + "layer_types": null, + "apply_wd_to_qk_layernorm": false, + "mrope_interleaved": true, + "add_version": false + } +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/added_tokens.json b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/args.json b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/args.json new file mode 100644 index 0000000000000000000000000000000000000000..483c814a0d63e8a1b3d0362c9c04f3e4d85798c4 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/args.json @@ -0,0 +1,704 @@ +{ + "use_ray": false, + "ray_exp_name": null, + "device_groups": null, + "model": "checkpoints/Qwen3-VL-30B-A3B-Instruct", + "model_type": "qwen3_moe_vl", + "model_revision": null, + "task_type": "causal_lm", + "torch_dtype": "bfloat16", + "attn_impl": null, + "new_special_tokens": [], + "num_labels": null, + "problem_type": null, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_type": "default" + }, + "device_map": null, + "max_memory": {}, + "max_model_len": null, + "local_repo_path": null, + "init_strategy": null, + "template": "qwen3_vl", + "system": null, + "max_length": 8192, + "truncation_strategy": "delete", + "max_pixels": null, + "agent_template": null, + "norm_bbox": null, + "use_chat_template": true, + "padding_side": "right", + "padding_free": true, + "loss_scale": "default", + "sequence_parallel_size": 1, + "template_backend": "swift", + "response_prefix": null, + "enable_thinking": null, + "add_non_thinking_prefix": true, + "dataset": [ + "highlight_batch1" + ], + "val_dataset": [], + "cached_dataset": [], + "cached_val_dataset": [], + "split_dataset_ratio": 0.0, + "data_seed": 42, + "dataset_num_proc": 8, + "load_from_cache_file": false, + "dataset_shuffle": true, + "val_dataset_shuffle": false, + "streaming": false, + "interleave_prob": null, + "stopping_strategy": "first_exhausted", + "shuffle_buffer_size": 1000, + "download_mode": "reuse_dataset_if_exists", + "columns": {}, + "strict": false, + "remove_unused_columns": true, + "model_name": null, + "model_author": null, + "custom_dataset_info": [], + "quant_method": null, + "quant_bits": null, + "hqq_axis": null, + "bnb_4bit_compute_dtype": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "max_new_tokens": null, + "temperature": 0.9, + "top_k": 50, + "top_p": 0.9, + "repetition_penalty": 1.0, + "num_beams": 1, + "stream": false, + "stop_words": [], + "logprobs": false, + "top_logprobs": null, + "structured_outputs_regex": null, + "ckpt_dir": null, + "lora_modules": [], + "tuner_backend": "peft", + "train_type": "lora", + "adapters": [], + "external_plugins": [], + "seed": 42, + "model_kwargs": {}, + "load_args": false, + "load_data_args": false, + "packing": false, + "packing_length": null, + "packing_num_proc": 1, + "lazy_tokenize": true, + "custom_register_path": [ + "ms-swift/custom_video_dataset_base.py" + ], + "use_hf": false, + "hub_token": null, + "ddp_timeout": 18000000, + "ddp_backend": null, + "ignore_args_error": false, + "use_swift_lora": false, + "freeze_llm": false, + "freeze_vit": true, + "freeze_aligner": true, + "freeze_parameters": [], + "freeze_parameters_regex": null, + "freeze_parameters_ratio": 0.0, + "trainable_parameters": [], + "trainable_parameters_regex": null, + "adapter_load": null, + "target_modules": [ + "all-linear" + ], + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias": "none", + "lora_dtype": null, + "use_rslora": false, + "rlhf_type": null, + "ref_load": null, + "ref_adapter_load": null, + "beta": null, + "rpo_alpha": null, + "reference_free": false, + "label_smoothing": 0.0, + "f_divergence_type": "reverse_kl", + "loss_type": null, + "desirable_weight": 1.0, + "undesirable_weight": 1.0, + "calculate_KL": null, + "center_rewards_coefficient": null, + "teacher_model": null, + "teacher_model_type": null, + "teacher_model_revision": null, + "lmbda": 0.5, + "seq_kd": false, + "offload_teacher_model": false, + "sft_alpha": 0.0, + "generation_batch_size": null, + "steps_per_generation": null, + "num_generations": 8, + "num_generations_eval": null, + "max_completion_length": 512, + "importance_sampling_level": "token", + "tau_pos": 1.0, + "tau_neg": 1.05, + "epsilon": 0.2, + "epsilon_high": null, + "delta": null, + "use_vllm": true, + "vllm_mode": null, + "vllm_enable_prefix_caching": true, + "vllm_gpu_memory_utilization": 0.9, + "vllm_tensor_parallel_size": 1, + "vllm_max_model_len": null, + "vllm_enforce_eager": false, + "vllm_limit_mm_per_prompt": null, + "vllm_disable_cascade_attn": false, + "vllm_max_num_seqs": null, + "vllm_mm_processor_cache_gb": null, + "vllm_engine_kwargs": null, + "sleep_level": 0, + "offload_optimizer": false, + "offload_model": false, + "offload_bridge": false, + "vllm_server_base_url": null, + "vllm_server_host": null, + "vllm_server_port": [ + 8000 + ], + "vllm_server_timeout": 240.0, + "vllm_server_group_port": null, + "reward_funcs": [], + "reward_weights": null, + "cosine_min_len_value_wrong": -0.5, + "cosine_max_len_value_wrong": 0.0, + "cosine_min_len_value_correct": 1.0, + "cosine_max_len_value_correct": 0.5, + "cosine_max_len": null, + "repetition_n_grams": 3, + "repetition_max_penalty": -1.0, + "soft_max_length": null, + "soft_cache_length": null, + "dynamic_sample": false, + "max_resample_times": 3, + "overlong_filter": false, + "scale_rewards": "group", + "advantage_estimator": "grpo", + "kl_in_reward": false, + "wandb_log_unique_prompts": null, + "log_completions": false, + "rollout_importance_sampling_mode": null, + "rollout_importance_sampling_threshold": 2.0, + "log_rollout_offpolicy_metrics": false, + "off_policy_sequence_mask_delta": null, + "log_entropy": false, + "top_entropy_quantile": 1.0, + "reward_model": null, + "reward_model_plugin": null, + "sync_ref_model": false, + "ref_model_sync_steps": 512, + "ref_model_mixup_alpha": 0.6, + "async_generate": false, + "move_model_batches": null, + "multi_turn_scheduler": null, + "max_turns": null, + "completion_length_limit_scope": "per_round", + "vllm_server_pass_dataset": false, + "num_iterations": 1, + "check_model": true, + "padded_vocab_size": 151936, + "initialize_embedding": false, + "mlp_padding_free": false, + "load_safetensors": true, + "save_safetensors": true, + "ref_model": null, + "ref_adapters": [], + "merge_lora": true, + "max_shard_size": "5GB", + "train_dataloader_shuffle": true, + "dataloader_pin_memory": true, + "dataloader_persistent_workers": true, + "dataloader_prefetch_factor": 2, + "group_by_length": false, + "architectures": "Qwen3VLMoeForConditionalGeneration", + "llm_architectures": "Qwen3VLMoeForConditionalGeneration", + "max_epochs": 4, + "enable_dft_loss": false, + "enable_channel_loss": false, + "save_strategy": "steps", + "original_max_position_embeddings": null, + "partial_rotary_factor": null, + "use_shared_expert_gate": false, + "report_to": "wandb", + "vit_gradient_checkpointing": true, + "vit_lr": null, + "aligner_lr": null, + "gradient_checkpointing_kwargs": null, + "linear_num_value_heads": null, + "linear_num_key_heads": null, + "linear_key_head_dim": null, + "linear_value_head_dim": null, + "linear_conv_kernel_dim": null, + "layer_types": null, + "apply_wd_to_qk_layernorm": false, + "mrope_interleaved": true, + "micro_batch_size": 2, + "global_batch_size": 16, + "recompute_granularity": "full", + "recompute_method": "uniform", + "recompute_num_layers": 1, + "recompute_modules": [ + "core_attn" + ], + "use_cpu_initialization": false, + "deterministic_mode": false, + "train_iters": null, + "log_interval": 5, + "tensorboard_dir": "/mnt/bn/strategy-mllm-train/user/tanyue/models/ckpts/qwen3vl_30b_highlight_batch1_epoch4_lora/runs", + "no_masked_softmax_fusion": false, + "no_bias_dropout_fusion": false, + "no_bias_swiglu_fusion": false, + "no_rope_fusion": false, + "no_gradient_accumulation_fusion": true, + "cross_entropy_loss_fusion": true, + "cross_entropy_fusion_impl": "native", + "calculate_per_token_loss": true, + "use_flash_attn": false, + "attention_backend": "flash", + "optimizer": "adam", + "optimizer_cpu_offload": false, + "optimizer_offload_fraction": 1.0, + "use_precision_aware_optimizer": false, + "main_grads_dtype": "fp32", + "main_params_dtype": "fp32", + "exp_avg_dtype": "fp32", + "exp_avg_sq_dtype": "fp32", + "dataloader_type": "cyclic", + "manual_gc": false, + "manual_gc_interval": 0, + "lr": 1e-05, + "lr_decay_style": "cosine", + "lr_decay_iters": null, + "lr_warmup_iters": 0, + "lr_warmup_fraction": 0.05, + "min_lr": 1e-06, + "weight_decay": 0.1, + "clip_grad": 1.0, + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_eps": 1e-08, + "sgd_momentum": 0.9, + "save": "/mnt/bn/strategy-mllm-train/user/tanyue/models/ckpts/qwen3vl_30b_highlight_batch1_epoch4_lora", + "save_interval": 2000, + "save_retain_interval": null, + "no_save_optim": true, + "no_save_rng": true, + "load": null, + "no_load_optim": false, + "no_load_rng": false, + "finetune": true, + "ckpt_format": "torch_dist", + "no_initialization": true, + "auto_detect_ckpt_format": true, + "exit_on_missing_checkpoint": true, + "async_save": false, + "use_persistent_ckpt_worker": false, + "ckpt_fully_parallel_load": false, + "ckpt_assume_constant_structure": false, + "distributed_backend": "nccl", + "local_rank": 0, + "use_distributed_optimizer": true, + "tensor_model_parallel_size": 4, + "pipeline_model_parallel_size": 1, + "decoder_first_pipeline_num_layers": null, + "decoder_last_pipeline_num_layers": null, + "account_for_embedding_in_pipeline_split": false, + "account_for_loss_in_pipeline_split": false, + "sequence_parallel": true, + "context_parallel_size": 1, + "tp_comm_overlap": false, + "overlap_grad_reduce": false, + "overlap_param_gather": false, + "distributed_timeout_minutes": 300000, + "num_layers_per_virtual_pipeline_stage": null, + "num_virtual_stages_per_pipeline_rank": null, + "microbatch_group_size_per_virtual_pipeline_stage": null, + "pipeline_model_parallel_layout": null, + "num_layers": 48, + "hidden_size": 2048, + "ffn_hidden_size": null, + "num_attention_heads": 32, + "group_query_attention": true, + "num_query_groups": 4, + "softmax_type": "vanilla", + "window_size": null, + "window_attn_skip_freq": null, + "max_position_embeddings": 262144, + "position_embedding_type": "mrope", + "mrope_section": [ + 24, + 20, + 20 + ], + "rotary_base": 5000000, + "rotary_percent": 1.0, + "rotary_interleaved": false, + "normalization": "RMSNorm", + "norm_epsilon": 1e-06, + "swiglu": true, + "quick_geglu": false, + "activation_func_clamp_value": null, + "glu_linear_offset": 0.0, + "untie_embeddings_and_output_weights": true, + "disable_bias_linear": true, + "add_qkv_bias": false, + "attention_dropout": 0.0, + "hidden_dropout": 0.0, + "kv_channels": 128, + "qk_layernorm": true, + "qk_l2_norm": null, + "no_rope_freq": null, + "moe_apply_probs_on_input": null, + "transformer_impl": "transformer_engine", + "num_experts": 128, + "moe_layer_freq": 1, + "moe_ffn_hidden_size": 768, + "moe_shared_expert_intermediate_size": null, + "moe_router_topk": 8, + "moe_router_num_groups": null, + "moe_router_group_topk": null, + "moe_router_pre_softmax": false, + "moe_router_dtype": "fp32", + "moe_router_score_function": "softmax", + "moe_router_bias_update_rate": null, + "moe_router_enable_expert_bias": false, + "moe_router_topk_scaling_factor": null, + "moe_router_load_balancing_type": "aux_loss", + "expert_model_parallel_size": 8, + "expert_tensor_parallel_size": 1, + "moe_token_dispatcher_type": null, + "moe_enable_deepep": false, + "moe_grouped_gemm": true, + "moe_permute_fusion": true, + "moe_aux_loss_coeff": 1e-06, + "moe_z_loss_coeff": null, + "moe_shared_expert_overlap": true, + "moe_layer_recompute": false, + "moe_expert_capacity_factor": 2.0, + "moe_pad_expert_input_to_capacity": false, + "moe_token_drop_policy": null, + "multi_latent_attention": false, + "q_lora_rank": null, + "kv_lora_rank": 32, + "qk_head_dim": 128, + "qk_pos_emb_head_dim": 64, + "mtp_num_layers": null, + "mtp_loss_scaling_factor": 0.1, + "fp8_format": null, + "fp8_recipe": "delayed", + "fp8_amax_history_len": 1024, + "fp8_amax_compute_algo": "max", + "fp8_param_gather": false, + "fp16": false, + "bf16": true, + "apply_query_key_layer_scaling": false, + "attention_softmax_in_fp32": true, + "log_params_norm": false, + "log_throughput": false, + "tensorboard_log_interval": 1, + "tensorboard_queue_size": 50, + "log_timers_to_tensorboard": true, + "no_log_learning_rate_to_tensorboard": false, + "log_validation_ppl_to_tensorboard": true, + "log_memory_to_tensorboard": true, + "logging_level": null, + "wandb_project": "megatron-swift", + "wandb_exp_name": "/mnt/bn/strategy-mllm-train/user/tanyue/models/ckpts/qwen3vl_30b_highlight_batch1_epoch4_lora", + "wandb_save_dir": null, + "eval_iters": -1, + "eval_interval": 2000, + "seq_length": 8192, + "num_workers": 8, + "no_data_sharding": false, + "megatron_extra_kwargs": {}, + "add_version": false, + "rank": 0, + "global_world_size": 8, + "local_world_size": 8, + "model_suffix": "Qwen3-VL-30B-A3B-Instruct", + "model_info": "ModelInfo(model_type='qwen3_moe_vl', model_dir='/opt/tiger/tanyue/highlight_tools/checkpoints/Qwen3-VL-30B-A3B-Instruct', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default'}, is_moe_model=True, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)", + "model_meta": "ModelMeta(model_type='qwen3_moe_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_vl', get_function=, model_arch=MultiModelKeys(arch_name='qwen3_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen3VLMoeForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])", + "model_dir": "/opt/tiger/tanyue/highlight_tools/checkpoints/Qwen3-VL-30B-A3B-Instruct", + "_val_dataset_exists": [], + "hub": "", + "megatron_model_meta": "MegatronModelMeta(megatron_model_type='qwen3_vl', model_types=['qwen3_vl', 'qwen3_moe_vl'], is_multimodal=True, bridge_cls=, model_cls=, get_transformer_layer_spec=None, model_provider=, visual_cls=, get_mtp_block_spec=None, extra_args_provider=None)", + "extra_args": { + "model_dir": "/opt/tiger/tanyue/highlight_tools/checkpoints/Qwen3-VL-30B-A3B-Instruct", + "is_multimodal": true, + "hf_model_type": "qwen3_moe_vl", + "use_ray": false, + "ray_exp_name": null, + "device_groups": null, + "model": "checkpoints/Qwen3-VL-30B-A3B-Instruct", + "model_type": "qwen3_moe_vl", + "model_revision": null, + "task_type": "causal_lm", + "torch_dtype": "bfloat16", + "attn_impl": null, + "new_special_tokens": [], + "num_labels": null, + "problem_type": null, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_type": "default" + }, + "device_map": null, + "max_memory": {}, + "max_model_len": null, + "local_repo_path": null, + "init_strategy": null, + "template": "qwen3_vl", + "system": null, + "max_length": 8192, + "truncation_strategy": "delete", + "max_pixels": null, + "agent_template": null, + "norm_bbox": null, + "use_chat_template": true, + "padding_side": "right", + "padding_free": true, + "sequence_parallel_size": 1, + "template_backend": "swift", + "response_prefix": null, + "enable_thinking": null, + "add_non_thinking_prefix": true, + "dataset": [ + "highlight_batch1" + ], + "val_dataset": [], + "cached_dataset": [], + "cached_val_dataset": [], + "split_dataset_ratio": 0.0, + "data_seed": 42, + "dataset_num_proc": 8, + "load_from_cache_file": false, + "dataset_shuffle": true, + "val_dataset_shuffle": false, + "streaming": false, + "interleave_prob": null, + "stopping_strategy": "first_exhausted", + "shuffle_buffer_size": 1000, + "download_mode": "reuse_dataset_if_exists", + "columns": {}, + "strict": false, + "remove_unused_columns": true, + "model_name": null, + "model_author": null, + "custom_dataset_info": [], + "quant_method": null, + "quant_bits": null, + "hqq_axis": null, + "bnb_4bit_compute_dtype": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "max_new_tokens": null, + "temperature": 0.9, + "top_k": 50, + "top_p": 0.9, + "repetition_penalty": 1.0, + "num_beams": 1, + "stream": false, + "stop_words": [], + "logprobs": false, + "top_logprobs": null, + "structured_outputs_regex": null, + "ckpt_dir": null, + "lora_modules": [], + "tuner_backend": "peft", + "train_type": "lora", + "adapters": [], + "external_plugins": [], + "model_kwargs": {}, + "load_args": false, + "load_data_args": false, + "packing": false, + "packing_length": null, + "packing_num_proc": 1, + "lazy_tokenize": true, + "custom_register_path": [ + "ms-swift/custom_video_dataset_base.py" + ], + "use_hf": false, + "hub_token": null, + "ddp_timeout": 18000000, + "ddp_backend": null, + "ignore_args_error": false, + "use_swift_lora": false, + "freeze_llm": false, + "freeze_vit": true, + "freeze_aligner": true, + "freeze_parameters": [], + "freeze_parameters_regex": null, + "freeze_parameters_ratio": 0.0, + "trainable_parameters": [], + "trainable_parameters_regex": null, + "adapter_load": null, + "target_modules": [ + "all-linear" + ], + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias": "none", + "lora_dtype": null, + "use_rslora": false, + "rlhf_type": null, + "ref_load": null, + "ref_adapter_load": null, + "beta": null, + "rpo_alpha": null, + "reference_free": false, + "label_smoothing": 0.0, + "f_divergence_type": "reverse_kl", + "loss_type": null, + "desirable_weight": 1.0, + "undesirable_weight": 1.0, + "calculate_KL": null, + "center_rewards_coefficient": null, + "teacher_model": null, + "teacher_model_type": null, + "teacher_model_revision": null, + "lmbda": 0.5, + "seq_kd": false, + "offload_teacher_model": false, + "sft_alpha": 0.0, + "generation_batch_size": null, + "steps_per_generation": null, + "num_generations": 8, + "num_generations_eval": null, + "max_completion_length": 512, + "importance_sampling_level": "token", + "tau_pos": 1.0, + "tau_neg": 1.05, + "epsilon": 0.2, + "epsilon_high": null, + "delta": null, + "use_vllm": true, + "vllm_mode": null, + "vllm_enable_prefix_caching": true, + "vllm_gpu_memory_utilization": 0.9, + "vllm_tensor_parallel_size": 1, + "vllm_max_model_len": null, + "vllm_enforce_eager": false, + "vllm_limit_mm_per_prompt": null, + "vllm_disable_cascade_attn": false, + "vllm_max_num_seqs": null, + "vllm_mm_processor_cache_gb": null, + "vllm_engine_kwargs": null, + "sleep_level": 0, + "offload_optimizer": false, + "offload_model": false, + "offload_bridge": false, + "vllm_server_base_url": null, + "vllm_server_host": null, + "vllm_server_port": [ + 8000 + ], + "vllm_server_timeout": 240.0, + "vllm_server_group_port": null, + "reward_funcs": [], + "reward_weights": null, + "cosine_min_len_value_wrong": -0.5, + "cosine_max_len_value_wrong": 0.0, + "cosine_min_len_value_correct": 1.0, + "cosine_max_len_value_correct": 0.5, + "cosine_max_len": null, + "repetition_n_grams": 3, + "repetition_max_penalty": -1.0, + "soft_max_length": null, + "soft_cache_length": null, + "dynamic_sample": false, + "max_resample_times": 3, + "overlong_filter": false, + "scale_rewards": "group", + "advantage_estimator": "grpo", + "kl_in_reward": false, + "wandb_log_unique_prompts": null, + "log_completions": false, + "rollout_importance_sampling_mode": null, + "rollout_importance_sampling_threshold": 2.0, + "log_rollout_offpolicy_metrics": false, + "off_policy_sequence_mask_delta": null, + "log_entropy": false, + "top_entropy_quantile": 1.0, + "reward_model": null, + "reward_model_plugin": null, + "sync_ref_model": false, + "ref_model_sync_steps": 512, + "ref_model_mixup_alpha": 0.6, + "async_generate": false, + "move_model_batches": null, + "multi_turn_scheduler": null, + "max_turns": null, + "completion_length_limit_scope": "per_round", + "vllm_server_pass_dataset": false, + "num_iterations": 1, + "check_model": true, + "padded_vocab_size": 151936, + "initialize_embedding": false, + "mlp_padding_free": false, + "load_safetensors": true, + "save_safetensors": true, + "ref_model": null, + "ref_adapters": [], + "merge_lora": true, + "max_shard_size": "5GB", + "train_dataloader_shuffle": true, + "dataloader_pin_memory": true, + "dataloader_persistent_workers": true, + "dataloader_prefetch_factor": 2, + "group_by_length": false, + "architectures": "Qwen3VLMoeForConditionalGeneration", + "llm_architectures": "Qwen3VLMoeForConditionalGeneration", + "max_epochs": 4, + "enable_dft_loss": false, + "enable_channel_loss": false, + "save_strategy": "steps", + "original_max_position_embeddings": null, + "partial_rotary_factor": null, + "use_shared_expert_gate": false, + "report_to": "wandb", + "vit_gradient_checkpointing": true, + "vit_lr": null, + "aligner_lr": null, + "gradient_checkpointing_kwargs": null, + "linear_num_value_heads": null, + "linear_num_key_heads": null, + "linear_key_head_dim": null, + "linear_value_head_dim": null, + "linear_conv_kernel_dim": null, + "layer_types": null, + "apply_wd_to_qk_layernorm": false, + "mrope_interleaved": true, + "add_version": false + } +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/chat_template.jinja b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/config.json b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/config.json new file mode 100644 index 0000000000000000000000000000000000000000..b0a6ccdb1e5f9ddc61485e04a3a7766b46ee855c --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/config.json @@ -0,0 +1,76 @@ +{ + "architectures": [ + "Qwen3VLMoeForConditionalGeneration" + ], + "dtype": "bfloat16", + "hidden_size": 2048, + "image_token_id": 151655, + "model_type": "qwen3_vl_moe", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "decoder_sparse_step": 1, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "max_position_embeddings": 262144, + "mlp_only_layers": [], + "model_type": "qwen3_vl_moe_text", + "moe_intermediate_size": 768, + "norm_topk_prob": true, + "num_attention_heads": 32, + "num_experts": 128, + "num_experts_per_tok": 8, + "num_hidden_layers": 48, + "num_key_value_heads": 4, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_type": "default" + }, + "rope_theta": 5000000, + "router_aux_loss_coef": 0.001, + "use_cache": true, + "vocab_size": 151936 + }, + "tie_word_embeddings": false, + "transformers_version": "4.57.6", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 8, + 16, + 24 + ], + "depth": 27, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4304, + "model_type": "qwen3_vl_moe", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2048, + "pad_token_id": 151643, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652, + "vocab_size": 151936 +} diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/iter_0000959/common.pt b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/iter_0000959/common.pt new file mode 100644 index 0000000000000000000000000000000000000000..3657a5eae8972ce7e4f4efe8eb9c1c8c5f4a5bcf --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/iter_0000959/common.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6b97c658ad564b5f8d37491f455e637870b9ff066042999a2598046c02a58a0 +size 28135 diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/latest_checkpointed_iteration.txt b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/latest_checkpointed_iteration.txt new file mode 100644 index 0000000000000000000000000000000000000000..a8a24cbb2ffcae486289780635dbae63b23a0476 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/latest_checkpointed_iteration.txt @@ -0,0 +1 @@ +959 \ No newline at end of file diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/model.safetensors.index.json b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..8e4a527923fdd0d0160b588bffcf97547fbb6643 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/model.safetensors.index.json @@ -0,0 +1,889 @@ +{ + "metadata": { + "total_size": 62141508064 + }, + "weight_map": { + "model.language_model.embed_tokens.weight": "model-00001-of-00013.safetensors", + "model.visual.patch_embed.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.patch_embed.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.pos_embed.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.norm1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.norm1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.norm2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.norm2.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00013.safetensors", + "model.visual.merger.norm.bias": "model-00001-of-00013.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00013.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.mlp.gate.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.mlp.experts.down_proj": "model-00001-of-00013.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.mlp.gate.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.mlp.experts.down_proj": "model-00001-of-00013.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.mlp.gate.weight": "model-00001-of-00013.safetensors", + "model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.2.mlp.experts.down_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.mlp.gate.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.mlp.experts.down_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.mlp.gate.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.mlp.experts.down_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.mlp.gate.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.mlp.experts.down_proj": "model-00002-of-00013.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.mlp.gate.weight": "model-00002-of-00013.safetensors", + "model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.6.mlp.experts.down_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.mlp.gate.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.mlp.experts.down_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.mlp.gate.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.mlp.experts.down_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.mlp.gate.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.mlp.experts.down_proj": "model-00003-of-00013.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.mlp.gate.weight": "model-00003-of-00013.safetensors", + "model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.10.mlp.experts.down_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.mlp.gate.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.mlp.experts.down_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.mlp.gate.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.mlp.experts.down_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.mlp.gate.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.mlp.experts.down_proj": "model-00004-of-00013.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.mlp.gate.weight": "model-00004-of-00013.safetensors", + "model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.14.mlp.experts.down_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.mlp.gate.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.mlp.experts.down_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.mlp.gate.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.mlp.experts.down_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.mlp.gate.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.mlp.experts.down_proj": "model-00005-of-00013.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.mlp.gate.weight": "model-00005-of-00013.safetensors", + "model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.18.mlp.experts.down_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.mlp.gate.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.mlp.experts.down_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.mlp.gate.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.mlp.experts.down_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.mlp.gate.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.mlp.experts.down_proj": "model-00006-of-00013.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.mlp.gate.weight": "model-00006-of-00013.safetensors", + "model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.22.mlp.experts.down_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.mlp.gate.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.mlp.experts.down_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.mlp.gate.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.mlp.experts.down_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.mlp.gate.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.mlp.experts.down_proj": "model-00007-of-00013.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.mlp.gate.weight": "model-00007-of-00013.safetensors", + "model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.26.mlp.experts.down_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.mlp.gate.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.mlp.experts.down_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.mlp.gate.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.mlp.experts.down_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.mlp.gate.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.mlp.experts.down_proj": "model-00008-of-00013.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.mlp.gate.weight": "model-00008-of-00013.safetensors", + "model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.30.mlp.experts.down_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.mlp.gate.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.mlp.experts.down_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.mlp.gate.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.mlp.experts.down_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.mlp.gate.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.mlp.experts.down_proj": "model-00009-of-00013.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.mlp.gate.weight": "model-00009-of-00013.safetensors", + "model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.34.mlp.experts.down_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.mlp.gate.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.mlp.experts.down_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.mlp.gate.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.mlp.experts.down_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.36.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.mlp.gate.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.mlp.experts.down_proj": "model-00010-of-00013.safetensors", + "model.language_model.layers.37.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.mlp.gate.weight": "model-00010-of-00013.safetensors", + "model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.38.mlp.experts.down_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.38.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.mlp.gate.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.mlp.experts.down_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.39.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.mlp.gate.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.mlp.experts.down_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.40.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.mlp.gate.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.mlp.experts.down_proj": "model-00011-of-00013.safetensors", + "model.language_model.layers.41.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.mlp.gate.weight": "model-00011-of-00013.safetensors", + "model.language_model.layers.42.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.42.mlp.experts.down_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.42.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.mlp.gate.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.mlp.experts.down_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.43.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.mlp.gate.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.mlp.experts.down_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.44.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.mlp.gate.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.mlp.experts.down_proj": "model-00012-of-00013.safetensors", + "model.language_model.layers.45.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.mlp.gate.weight": "model-00012-of-00013.safetensors", + "model.language_model.layers.46.mlp.experts.gate_up_proj": "model-00013-of-00013.safetensors", + "model.language_model.layers.46.mlp.experts.down_proj": "model-00013-of-00013.safetensors", + "model.language_model.layers.46.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.self_attn.q_norm.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.self_attn.k_norm.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.input_layernorm.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.mlp.gate.weight": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.mlp.experts.gate_up_proj": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.mlp.experts.down_proj": "model-00013-of-00013.safetensors", + "model.language_model.layers.47.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", + "lm_head.weight": "model-00013-of-00013.safetensors", + "model.language_model.norm.weight": "model-00013-of-00013.safetensors" + } +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/preprocessor_config.json b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..2ea84a437d448ff71b08df68fdd949d5cc4ebb64 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/preprocessor_config.json @@ -0,0 +1,21 @@ +{ + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "patch_size": 16, + "temporal_patch_size": 2, + "merge_size": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "processor_class": "Qwen3VLProcessor", + "image_processor_type": "Qwen2VLImageProcessorFast" +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/special_tokens_map.json b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/tokenizer_config.json b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/video_preprocessor_config.json b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/video_preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e32b1d90356f74457edbfca27aa1e121dab7cdc7 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959-merged/video_preprocessor_config.json @@ -0,0 +1,41 @@ +{ + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" +} diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/args.json b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/args.json new file mode 100644 index 0000000000000000000000000000000000000000..483c814a0d63e8a1b3d0362c9c04f3e4d85798c4 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/args.json @@ -0,0 +1,704 @@ +{ + "use_ray": false, + "ray_exp_name": null, + "device_groups": null, + "model": "checkpoints/Qwen3-VL-30B-A3B-Instruct", + "model_type": "qwen3_moe_vl", + "model_revision": null, + "task_type": "causal_lm", + "torch_dtype": "bfloat16", + "attn_impl": null, + "new_special_tokens": [], + "num_labels": null, + "problem_type": null, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_type": "default" + }, + "device_map": null, + "max_memory": {}, + "max_model_len": null, + "local_repo_path": null, + "init_strategy": null, + "template": "qwen3_vl", + "system": null, + "max_length": 8192, + "truncation_strategy": "delete", + "max_pixels": null, + "agent_template": null, + "norm_bbox": null, + "use_chat_template": true, + "padding_side": "right", + "padding_free": true, + "loss_scale": "default", + "sequence_parallel_size": 1, + "template_backend": "swift", + "response_prefix": null, + "enable_thinking": null, + "add_non_thinking_prefix": true, + "dataset": [ + "highlight_batch1" + ], + "val_dataset": [], + "cached_dataset": [], + "cached_val_dataset": [], + "split_dataset_ratio": 0.0, + "data_seed": 42, + "dataset_num_proc": 8, + "load_from_cache_file": false, + "dataset_shuffle": true, + "val_dataset_shuffle": false, + "streaming": false, + "interleave_prob": null, + "stopping_strategy": "first_exhausted", + "shuffle_buffer_size": 1000, + "download_mode": "reuse_dataset_if_exists", + "columns": {}, + "strict": false, + "remove_unused_columns": true, + "model_name": null, + "model_author": null, + "custom_dataset_info": [], + "quant_method": null, + "quant_bits": null, + "hqq_axis": null, + "bnb_4bit_compute_dtype": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "max_new_tokens": null, + "temperature": 0.9, + "top_k": 50, + "top_p": 0.9, + "repetition_penalty": 1.0, + "num_beams": 1, + "stream": false, + "stop_words": [], + "logprobs": false, + "top_logprobs": null, + "structured_outputs_regex": null, + "ckpt_dir": null, + "lora_modules": [], + "tuner_backend": "peft", + "train_type": "lora", + "adapters": [], + "external_plugins": [], + "seed": 42, + "model_kwargs": {}, + "load_args": false, + "load_data_args": false, + "packing": false, + "packing_length": null, + "packing_num_proc": 1, + "lazy_tokenize": true, + "custom_register_path": [ + "ms-swift/custom_video_dataset_base.py" + ], + "use_hf": false, + "hub_token": null, + "ddp_timeout": 18000000, + "ddp_backend": null, + "ignore_args_error": false, + "use_swift_lora": false, + "freeze_llm": false, + "freeze_vit": true, + "freeze_aligner": true, + "freeze_parameters": [], + "freeze_parameters_regex": null, + "freeze_parameters_ratio": 0.0, + "trainable_parameters": [], + "trainable_parameters_regex": null, + "adapter_load": null, + "target_modules": [ + "all-linear" + ], + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias": "none", + "lora_dtype": null, + "use_rslora": false, + "rlhf_type": null, + "ref_load": null, + "ref_adapter_load": null, + "beta": null, + "rpo_alpha": null, + "reference_free": false, + "label_smoothing": 0.0, + "f_divergence_type": "reverse_kl", + "loss_type": null, + "desirable_weight": 1.0, + "undesirable_weight": 1.0, + "calculate_KL": null, + "center_rewards_coefficient": null, + "teacher_model": null, + "teacher_model_type": null, + "teacher_model_revision": null, + "lmbda": 0.5, + "seq_kd": false, + "offload_teacher_model": false, + "sft_alpha": 0.0, + "generation_batch_size": null, + "steps_per_generation": null, + "num_generations": 8, + "num_generations_eval": null, + "max_completion_length": 512, + "importance_sampling_level": "token", + "tau_pos": 1.0, + "tau_neg": 1.05, + "epsilon": 0.2, + "epsilon_high": null, + "delta": null, + "use_vllm": true, + "vllm_mode": null, + "vllm_enable_prefix_caching": true, + "vllm_gpu_memory_utilization": 0.9, + "vllm_tensor_parallel_size": 1, + "vllm_max_model_len": null, + "vllm_enforce_eager": false, + "vllm_limit_mm_per_prompt": null, + "vllm_disable_cascade_attn": false, + "vllm_max_num_seqs": null, + "vllm_mm_processor_cache_gb": null, + "vllm_engine_kwargs": null, + "sleep_level": 0, + "offload_optimizer": false, + "offload_model": false, + "offload_bridge": false, + "vllm_server_base_url": null, + "vllm_server_host": null, + "vllm_server_port": [ + 8000 + ], + "vllm_server_timeout": 240.0, + "vllm_server_group_port": null, + "reward_funcs": [], + "reward_weights": null, + "cosine_min_len_value_wrong": -0.5, + "cosine_max_len_value_wrong": 0.0, + "cosine_min_len_value_correct": 1.0, + "cosine_max_len_value_correct": 0.5, + "cosine_max_len": null, + "repetition_n_grams": 3, + "repetition_max_penalty": -1.0, + "soft_max_length": null, + "soft_cache_length": null, + "dynamic_sample": false, + "max_resample_times": 3, + "overlong_filter": false, + "scale_rewards": "group", + "advantage_estimator": "grpo", + "kl_in_reward": false, + "wandb_log_unique_prompts": null, + "log_completions": false, + "rollout_importance_sampling_mode": null, + "rollout_importance_sampling_threshold": 2.0, + "log_rollout_offpolicy_metrics": false, + "off_policy_sequence_mask_delta": null, + "log_entropy": false, + "top_entropy_quantile": 1.0, + "reward_model": null, + "reward_model_plugin": null, + "sync_ref_model": false, + "ref_model_sync_steps": 512, + "ref_model_mixup_alpha": 0.6, + "async_generate": false, + "move_model_batches": null, + "multi_turn_scheduler": null, + "max_turns": null, + "completion_length_limit_scope": "per_round", + "vllm_server_pass_dataset": false, + "num_iterations": 1, + "check_model": true, + "padded_vocab_size": 151936, + "initialize_embedding": false, + "mlp_padding_free": false, + "load_safetensors": true, + "save_safetensors": true, + "ref_model": null, + "ref_adapters": [], + "merge_lora": true, + "max_shard_size": "5GB", + "train_dataloader_shuffle": true, + "dataloader_pin_memory": true, + "dataloader_persistent_workers": true, + "dataloader_prefetch_factor": 2, + "group_by_length": false, + "architectures": "Qwen3VLMoeForConditionalGeneration", + "llm_architectures": "Qwen3VLMoeForConditionalGeneration", + "max_epochs": 4, + "enable_dft_loss": false, + "enable_channel_loss": false, + "save_strategy": "steps", + "original_max_position_embeddings": null, + "partial_rotary_factor": null, + "use_shared_expert_gate": false, + "report_to": "wandb", + "vit_gradient_checkpointing": true, + "vit_lr": null, + "aligner_lr": null, + "gradient_checkpointing_kwargs": null, + "linear_num_value_heads": null, + "linear_num_key_heads": null, + "linear_key_head_dim": null, + "linear_value_head_dim": null, + "linear_conv_kernel_dim": null, + "layer_types": null, + "apply_wd_to_qk_layernorm": false, + "mrope_interleaved": true, + "micro_batch_size": 2, + "global_batch_size": 16, + "recompute_granularity": "full", + "recompute_method": "uniform", + "recompute_num_layers": 1, + "recompute_modules": [ + "core_attn" + ], + "use_cpu_initialization": false, + "deterministic_mode": false, + "train_iters": null, + "log_interval": 5, + "tensorboard_dir": "/mnt/bn/strategy-mllm-train/user/tanyue/models/ckpts/qwen3vl_30b_highlight_batch1_epoch4_lora/runs", + "no_masked_softmax_fusion": false, + "no_bias_dropout_fusion": false, + "no_bias_swiglu_fusion": false, + "no_rope_fusion": false, + "no_gradient_accumulation_fusion": true, + "cross_entropy_loss_fusion": true, + "cross_entropy_fusion_impl": "native", + "calculate_per_token_loss": true, + "use_flash_attn": false, + "attention_backend": "flash", + "optimizer": "adam", + "optimizer_cpu_offload": false, + "optimizer_offload_fraction": 1.0, + "use_precision_aware_optimizer": false, + "main_grads_dtype": "fp32", + "main_params_dtype": "fp32", + "exp_avg_dtype": "fp32", + "exp_avg_sq_dtype": "fp32", + "dataloader_type": "cyclic", + "manual_gc": false, + "manual_gc_interval": 0, + "lr": 1e-05, + "lr_decay_style": "cosine", + "lr_decay_iters": null, + "lr_warmup_iters": 0, + "lr_warmup_fraction": 0.05, + "min_lr": 1e-06, + "weight_decay": 0.1, + "clip_grad": 1.0, + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_eps": 1e-08, + "sgd_momentum": 0.9, + "save": "/mnt/bn/strategy-mllm-train/user/tanyue/models/ckpts/qwen3vl_30b_highlight_batch1_epoch4_lora", + "save_interval": 2000, + "save_retain_interval": null, + "no_save_optim": true, + "no_save_rng": true, + "load": null, + "no_load_optim": false, + "no_load_rng": false, + "finetune": true, + "ckpt_format": "torch_dist", + "no_initialization": true, + "auto_detect_ckpt_format": true, + "exit_on_missing_checkpoint": true, + "async_save": false, + "use_persistent_ckpt_worker": false, + "ckpt_fully_parallel_load": false, + "ckpt_assume_constant_structure": false, + "distributed_backend": "nccl", + "local_rank": 0, + "use_distributed_optimizer": true, + "tensor_model_parallel_size": 4, + "pipeline_model_parallel_size": 1, + "decoder_first_pipeline_num_layers": null, + "decoder_last_pipeline_num_layers": null, + "account_for_embedding_in_pipeline_split": false, + "account_for_loss_in_pipeline_split": false, + "sequence_parallel": true, + "context_parallel_size": 1, + "tp_comm_overlap": false, + "overlap_grad_reduce": false, + "overlap_param_gather": false, + "distributed_timeout_minutes": 300000, + "num_layers_per_virtual_pipeline_stage": null, + "num_virtual_stages_per_pipeline_rank": null, + "microbatch_group_size_per_virtual_pipeline_stage": null, + "pipeline_model_parallel_layout": null, + "num_layers": 48, + "hidden_size": 2048, + "ffn_hidden_size": null, + "num_attention_heads": 32, + "group_query_attention": true, + "num_query_groups": 4, + "softmax_type": "vanilla", + "window_size": null, + "window_attn_skip_freq": null, + "max_position_embeddings": 262144, + "position_embedding_type": "mrope", + "mrope_section": [ + 24, + 20, + 20 + ], + "rotary_base": 5000000, + "rotary_percent": 1.0, + "rotary_interleaved": false, + "normalization": "RMSNorm", + "norm_epsilon": 1e-06, + "swiglu": true, + "quick_geglu": false, + "activation_func_clamp_value": null, + "glu_linear_offset": 0.0, + "untie_embeddings_and_output_weights": true, + "disable_bias_linear": true, + "add_qkv_bias": false, + "attention_dropout": 0.0, + "hidden_dropout": 0.0, + "kv_channels": 128, + "qk_layernorm": true, + "qk_l2_norm": null, + "no_rope_freq": null, + "moe_apply_probs_on_input": null, + "transformer_impl": "transformer_engine", + "num_experts": 128, + "moe_layer_freq": 1, + "moe_ffn_hidden_size": 768, + "moe_shared_expert_intermediate_size": null, + "moe_router_topk": 8, + "moe_router_num_groups": null, + "moe_router_group_topk": null, + "moe_router_pre_softmax": false, + "moe_router_dtype": "fp32", + "moe_router_score_function": "softmax", + "moe_router_bias_update_rate": null, + "moe_router_enable_expert_bias": false, + "moe_router_topk_scaling_factor": null, + "moe_router_load_balancing_type": "aux_loss", + "expert_model_parallel_size": 8, + "expert_tensor_parallel_size": 1, + "moe_token_dispatcher_type": null, + "moe_enable_deepep": false, + "moe_grouped_gemm": true, + "moe_permute_fusion": true, + "moe_aux_loss_coeff": 1e-06, + "moe_z_loss_coeff": null, + "moe_shared_expert_overlap": true, + "moe_layer_recompute": false, + "moe_expert_capacity_factor": 2.0, + "moe_pad_expert_input_to_capacity": false, + "moe_token_drop_policy": null, + "multi_latent_attention": false, + "q_lora_rank": null, + "kv_lora_rank": 32, + "qk_head_dim": 128, + "qk_pos_emb_head_dim": 64, + "mtp_num_layers": null, + "mtp_loss_scaling_factor": 0.1, + "fp8_format": null, + "fp8_recipe": "delayed", + "fp8_amax_history_len": 1024, + "fp8_amax_compute_algo": "max", + "fp8_param_gather": false, + "fp16": false, + "bf16": true, + "apply_query_key_layer_scaling": false, + "attention_softmax_in_fp32": true, + "log_params_norm": false, + "log_throughput": false, + "tensorboard_log_interval": 1, + "tensorboard_queue_size": 50, + "log_timers_to_tensorboard": true, + "no_log_learning_rate_to_tensorboard": false, + "log_validation_ppl_to_tensorboard": true, + "log_memory_to_tensorboard": true, + "logging_level": null, + "wandb_project": "megatron-swift", + "wandb_exp_name": "/mnt/bn/strategy-mllm-train/user/tanyue/models/ckpts/qwen3vl_30b_highlight_batch1_epoch4_lora", + "wandb_save_dir": null, + "eval_iters": -1, + "eval_interval": 2000, + "seq_length": 8192, + "num_workers": 8, + "no_data_sharding": false, + "megatron_extra_kwargs": {}, + "add_version": false, + "rank": 0, + "global_world_size": 8, + "local_world_size": 8, + "model_suffix": "Qwen3-VL-30B-A3B-Instruct", + "model_info": "ModelInfo(model_type='qwen3_moe_vl', model_dir='/opt/tiger/tanyue/highlight_tools/checkpoints/Qwen3-VL-30B-A3B-Instruct', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default'}, is_moe_model=True, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)", + "model_meta": "ModelMeta(model_type='qwen3_moe_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_vl', get_function=, model_arch=MultiModelKeys(arch_name='qwen3_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen3VLMoeForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])", + "model_dir": "/opt/tiger/tanyue/highlight_tools/checkpoints/Qwen3-VL-30B-A3B-Instruct", + "_val_dataset_exists": [], + "hub": "", + "megatron_model_meta": "MegatronModelMeta(megatron_model_type='qwen3_vl', model_types=['qwen3_vl', 'qwen3_moe_vl'], is_multimodal=True, bridge_cls=, model_cls=, get_transformer_layer_spec=None, model_provider=, visual_cls=, get_mtp_block_spec=None, extra_args_provider=None)", + "extra_args": { + "model_dir": "/opt/tiger/tanyue/highlight_tools/checkpoints/Qwen3-VL-30B-A3B-Instruct", + "is_multimodal": true, + "hf_model_type": "qwen3_moe_vl", + "use_ray": false, + "ray_exp_name": null, + "device_groups": null, + "model": "checkpoints/Qwen3-VL-30B-A3B-Instruct", + "model_type": "qwen3_moe_vl", + "model_revision": null, + "task_type": "causal_lm", + "torch_dtype": "bfloat16", + "attn_impl": null, + "new_special_tokens": [], + "num_labels": null, + "problem_type": null, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_type": "default" + }, + "device_map": null, + "max_memory": {}, + "max_model_len": null, + "local_repo_path": null, + "init_strategy": null, + "template": "qwen3_vl", + "system": null, + "max_length": 8192, + "truncation_strategy": "delete", + "max_pixels": null, + "agent_template": null, + "norm_bbox": null, + "use_chat_template": true, + "padding_side": "right", + "padding_free": true, + "sequence_parallel_size": 1, + "template_backend": "swift", + "response_prefix": null, + "enable_thinking": null, + "add_non_thinking_prefix": true, + "dataset": [ + "highlight_batch1" + ], + "val_dataset": [], + "cached_dataset": [], + "cached_val_dataset": [], + "split_dataset_ratio": 0.0, + "data_seed": 42, + "dataset_num_proc": 8, + "load_from_cache_file": false, + "dataset_shuffle": true, + "val_dataset_shuffle": false, + "streaming": false, + "interleave_prob": null, + "stopping_strategy": "first_exhausted", + "shuffle_buffer_size": 1000, + "download_mode": "reuse_dataset_if_exists", + "columns": {}, + "strict": false, + "remove_unused_columns": true, + "model_name": null, + "model_author": null, + "custom_dataset_info": [], + "quant_method": null, + "quant_bits": null, + "hqq_axis": null, + "bnb_4bit_compute_dtype": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "max_new_tokens": null, + "temperature": 0.9, + "top_k": 50, + "top_p": 0.9, + "repetition_penalty": 1.0, + "num_beams": 1, + "stream": false, + "stop_words": [], + "logprobs": false, + "top_logprobs": null, + "structured_outputs_regex": null, + "ckpt_dir": null, + "lora_modules": [], + "tuner_backend": "peft", + "train_type": "lora", + "adapters": [], + "external_plugins": [], + "model_kwargs": {}, + "load_args": false, + "load_data_args": false, + "packing": false, + "packing_length": null, + "packing_num_proc": 1, + "lazy_tokenize": true, + "custom_register_path": [ + "ms-swift/custom_video_dataset_base.py" + ], + "use_hf": false, + "hub_token": null, + "ddp_timeout": 18000000, + "ddp_backend": null, + "ignore_args_error": false, + "use_swift_lora": false, + "freeze_llm": false, + "freeze_vit": true, + "freeze_aligner": true, + "freeze_parameters": [], + "freeze_parameters_regex": null, + "freeze_parameters_ratio": 0.0, + "trainable_parameters": [], + "trainable_parameters_regex": null, + "adapter_load": null, + "target_modules": [ + "all-linear" + ], + "target_regex": null, + "modules_to_save": [], + "lora_rank": 8, + "lora_alpha": 32, + "lora_dropout": 0.05, + "lora_bias": "none", + "lora_dtype": null, + "use_rslora": false, + "rlhf_type": null, + "ref_load": null, + "ref_adapter_load": null, + "beta": null, + "rpo_alpha": null, + "reference_free": false, + "label_smoothing": 0.0, + "f_divergence_type": "reverse_kl", + "loss_type": null, + "desirable_weight": 1.0, + "undesirable_weight": 1.0, + "calculate_KL": null, + "center_rewards_coefficient": null, + "teacher_model": null, + "teacher_model_type": null, + "teacher_model_revision": null, + "lmbda": 0.5, + "seq_kd": false, + "offload_teacher_model": false, + "sft_alpha": 0.0, + "generation_batch_size": null, + "steps_per_generation": null, + "num_generations": 8, + "num_generations_eval": null, + "max_completion_length": 512, + "importance_sampling_level": "token", + "tau_pos": 1.0, + "tau_neg": 1.05, + "epsilon": 0.2, + "epsilon_high": null, + "delta": null, + "use_vllm": true, + "vllm_mode": null, + "vllm_enable_prefix_caching": true, + "vllm_gpu_memory_utilization": 0.9, + "vllm_tensor_parallel_size": 1, + "vllm_max_model_len": null, + "vllm_enforce_eager": false, + "vllm_limit_mm_per_prompt": null, + "vllm_disable_cascade_attn": false, + "vllm_max_num_seqs": null, + "vllm_mm_processor_cache_gb": null, + "vllm_engine_kwargs": null, + "sleep_level": 0, + "offload_optimizer": false, + "offload_model": false, + "offload_bridge": false, + "vllm_server_base_url": null, + "vllm_server_host": null, + "vllm_server_port": [ + 8000 + ], + "vllm_server_timeout": 240.0, + "vllm_server_group_port": null, + "reward_funcs": [], + "reward_weights": null, + "cosine_min_len_value_wrong": -0.5, + "cosine_max_len_value_wrong": 0.0, + "cosine_min_len_value_correct": 1.0, + "cosine_max_len_value_correct": 0.5, + "cosine_max_len": null, + "repetition_n_grams": 3, + "repetition_max_penalty": -1.0, + "soft_max_length": null, + "soft_cache_length": null, + "dynamic_sample": false, + "max_resample_times": 3, + "overlong_filter": false, + "scale_rewards": "group", + "advantage_estimator": "grpo", + "kl_in_reward": false, + "wandb_log_unique_prompts": null, + "log_completions": false, + "rollout_importance_sampling_mode": null, + "rollout_importance_sampling_threshold": 2.0, + "log_rollout_offpolicy_metrics": false, + "off_policy_sequence_mask_delta": null, + "log_entropy": false, + "top_entropy_quantile": 1.0, + "reward_model": null, + "reward_model_plugin": null, + "sync_ref_model": false, + "ref_model_sync_steps": 512, + "ref_model_mixup_alpha": 0.6, + "async_generate": false, + "move_model_batches": null, + "multi_turn_scheduler": null, + "max_turns": null, + "completion_length_limit_scope": "per_round", + "vllm_server_pass_dataset": false, + "num_iterations": 1, + "check_model": true, + "padded_vocab_size": 151936, + "initialize_embedding": false, + "mlp_padding_free": false, + "load_safetensors": true, + "save_safetensors": true, + "ref_model": null, + "ref_adapters": [], + "merge_lora": true, + "max_shard_size": "5GB", + "train_dataloader_shuffle": true, + "dataloader_pin_memory": true, + "dataloader_persistent_workers": true, + "dataloader_prefetch_factor": 2, + "group_by_length": false, + "architectures": "Qwen3VLMoeForConditionalGeneration", + "llm_architectures": "Qwen3VLMoeForConditionalGeneration", + "max_epochs": 4, + "enable_dft_loss": false, + "enable_channel_loss": false, + "save_strategy": "steps", + "original_max_position_embeddings": null, + "partial_rotary_factor": null, + "use_shared_expert_gate": false, + "report_to": "wandb", + "vit_gradient_checkpointing": true, + "vit_lr": null, + "aligner_lr": null, + "gradient_checkpointing_kwargs": null, + "linear_num_value_heads": null, + "linear_num_key_heads": null, + "linear_key_head_dim": null, + "linear_value_head_dim": null, + "linear_conv_kernel_dim": null, + "layer_types": null, + "apply_wd_to_qk_layernorm": false, + "mrope_interleaved": true, + "add_version": false + } +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/iter_0000959/.metadata b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/iter_0000959/.metadata new file mode 100644 index 0000000000000000000000000000000000000000..05528b0293cc6b4c24ef9e5a576f97cbbcaf51ad Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/iter_0000959/.metadata differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/iter_0000959/common.pt b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/iter_0000959/common.pt new file mode 100644 index 0000000000000000000000000000000000000000..3657a5eae8972ce7e4f4efe8eb9c1c8c5f4a5bcf --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/iter_0000959/common.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6b97c658ad564b5f8d37491f455e637870b9ff066042999a2598046c02a58a0 +size 28135 diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/iter_0000959/metadata.json b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/iter_0000959/metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..c9dbde0bcf4d2d993122dcc7d6bcb1eef8b6fb77 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/iter_0000959/metadata.json @@ -0,0 +1 @@ +{"sharded_backend": "torch_dist", "sharded_backend_version": 1, "common_backend": "torch", "common_backend_version": 1} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/latest_checkpointed_iteration.txt b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/latest_checkpointed_iteration.txt new file mode 100644 index 0000000000000000000000000000000000000000..a8a24cbb2ffcae486289780635dbae63b23a0476 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/latest_checkpointed_iteration.txt @@ -0,0 +1 @@ +959 \ No newline at end of file diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/latest_wandb_artifact_path.txt b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/latest_wandb_artifact_path.txt new file mode 100644 index 0000000000000000000000000000000000000000..5945f2984fa88cb86fb97521912f313d10347937 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/checkpoint-959/latest_wandb_artifact_path.txt @@ -0,0 +1 @@ +/megatron-swift \ No newline at end of file diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/batch-size vs samples.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/batch-size vs samples.png new file mode 100644 index 0000000000000000000000000000000000000000..1931748b3a90a78413dff94655fd75eee45abfce Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/batch-size vs samples.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/batch-size.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/batch-size.png new file mode 100644 index 0000000000000000000000000000000000000000..520bf48d1dcba436d4fab229dc26433cc526a376 Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/batch-size.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/grad-norm vs samples.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/grad-norm vs samples.png new file mode 100644 index 0000000000000000000000000000000000000000..316e41a8d6c725b719b9fa6e85e3290e761d1fba Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/grad-norm vs samples.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/grad-norm.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/grad-norm.png new file mode 100644 index 0000000000000000000000000000000000000000..95e4feaf50d540c723012e946eab7fce4c64c4c1 Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/grad-norm.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/iteration-time.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/iteration-time.png new file mode 100644 index 0000000000000000000000000000000000000000..07a86a41e2d47fd3ef65f4471d7cf1103ae95694 Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/iteration-time.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/learning-rate vs samples.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/learning-rate vs samples.png new file mode 100644 index 0000000000000000000000000000000000000000..9458b87e3e319339b5cd8983b5e49c7c4dd6d587 Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/learning-rate vs samples.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/learning-rate.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/learning-rate.png new file mode 100644 index 0000000000000000000000000000000000000000..17d293eab7ae9a3a921f1d165d372f204fcd838f Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/learning-rate.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/lm loss vs samples.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/lm loss vs samples.png new file mode 100644 index 0000000000000000000000000000000000000000..e581d9c6cd03286910450380ae68683d449981ba Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/lm loss vs samples.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/lm loss.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/lm loss.png new file mode 100644 index 0000000000000000000000000000000000000000..c4223b7210f842b91d5d2ef59c3ebc099cdf98ef Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/lm loss.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/load_balancing_loss.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/load_balancing_loss.png new file mode 100644 index 0000000000000000000000000000000000000000..d7bfda76e3f193d6c5b9e569e749247adeae54d3 Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/load_balancing_loss.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/loss-scale vs samples.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/loss-scale vs samples.png new file mode 100644 index 0000000000000000000000000000000000000000..c6d96960d3a44d5d90b55476649c555c9ba0bad5 Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/loss-scale vs samples.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/loss-scale.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/loss-scale.png new file mode 100644 index 0000000000000000000000000000000000000000..0d1d4e5e645933ebf8408a66e89503ac0082548e Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/loss-scale.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/mem-allocated-bytes.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/mem-allocated-bytes.png new file mode 100644 index 0000000000000000000000000000000000000000..cac1c167ddfe0a82ad86cfcbb39e159f87271d31 Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/mem-allocated-bytes.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/mem-allocated-count.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/mem-allocated-count.png new file mode 100644 index 0000000000000000000000000000000000000000..0b2b164f53c0663829089f86e7e83125ccc6302d Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/mem-allocated-count.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/mem-max-allocated-bytes.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/mem-max-allocated-bytes.png new file mode 100644 index 0000000000000000000000000000000000000000..464e8ea44e0e3aa06d5f07f159e5607134c6d508 Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/mem-max-allocated-bytes.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/mem-reserved-bytes.png b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/mem-reserved-bytes.png new file mode 100644 index 0000000000000000000000000000000000000000..4ed6e95c57c0d9ee2fc63d14d35a82c3bb436979 Binary files /dev/null and b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/images/mem-reserved-bytes.png differ diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/logging.jsonl b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/logging.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..6c39621a8262e7d705cd9e40cb9bf7ca827f8091 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/logging.jsonl @@ -0,0 +1,349 @@ +{"lm loss": 2.06886578, "load_balancing_loss": 1.20992255, "grad_norm": 10.24453449, "learning_rate": 2.1e-07, "elapsed_time_per_iteration": 78.74745274, "memory(GiB)": 17.94, "elapsed_time": "1m 18s", "remaining_time": "20h 57m 20s", "loss_scale": 1.0, "consumed_samples": 16, "global_step/max_steps": "1/959"} +{"lm loss": 1.93440223, "load_balancing_loss": 1.20487761, "grad_norm": 10.06498718, "learning_rate": 1.04e-06, "elapsed_time_per_iteration": 15.36132926, "memory(GiB)": 18.01, "elapsed_time": "2m 20s", "remaining_time": "7h 25m 48s", "loss_scale": 1.0, "consumed_samples": 80, "global_step/max_steps": "5/959"} +{"lm loss": 1.94003792, "load_balancing_loss": 1.21111469, "grad_norm": 11.54757023, "learning_rate": 2.09e-06, "elapsed_time_per_iteration": 14.16489134, "memory(GiB)": 18.02, "elapsed_time": "3m 31s", "remaining_time": "5h 33m 45s", "loss_scale": 1.0, "consumed_samples": 160, "global_step/max_steps": "10/959"} +{"lm loss": 1.90085659, "load_balancing_loss": 1.21481504, "grad_norm": 10.51198196, "learning_rate": 3.13e-06, "elapsed_time_per_iteration": 14.37177467, "memory(GiB)": 18.04, "elapsed_time": "4m 42s", "remaining_time": "4h 56m 42s", "loss_scale": 1.0, "consumed_samples": 240, "global_step/max_steps": "15/959"} +{"lm loss": 1.81861343, "load_balancing_loss": 1.19527779, "grad_norm": 9.33597183, "learning_rate": 4.17e-06, "elapsed_time_per_iteration": 14.26105437, "memory(GiB)": 18.04, "elapsed_time": "5m 54s", "remaining_time": "4h 37m 8s", "loss_scale": 1.0, "consumed_samples": 320, "global_step/max_steps": "20/959"} +{"lm loss": 1.66903324, "load_balancing_loss": 1.22108479, "grad_norm": 8.97616768, "learning_rate": 5.21e-06, "elapsed_time_per_iteration": 13.34813857, "memory(GiB)": 20.83, "elapsed_time": "7m 0s", "remaining_time": "4h 22m 5s", "loss_scale": 1.0, "consumed_samples": 400, "global_step/max_steps": "25/959"} +{"lm loss": 1.40994349, "load_balancing_loss": 1.22919598, "grad_norm": 7.47540379, "learning_rate": 6.26e-06, "elapsed_time_per_iteration": 13.54675384, "memory(GiB)": 20.83, "elapsed_time": "8m 8s", "remaining_time": "4h 12m 12s", "loss_scale": 1.0, "consumed_samples": 480, "global_step/max_steps": "30/959"} +{"lm loss": 1.11348267, "load_balancing_loss": 1.19905396, "grad_norm": 5.16163731, "learning_rate": 7.3e-06, "elapsed_time_per_iteration": 14.263201, "memory(GiB)": 23.83, "elapsed_time": "9m 19s", "remaining_time": "4h 6m 23s", "loss_scale": 1.0, "consumed_samples": 560, "global_step/max_steps": "35/959"} +{"lm loss": 0.9235508, "load_balancing_loss": 1.20481243, "grad_norm": 3.51510406, "learning_rate": 8.34e-06, "elapsed_time_per_iteration": 14.18977175, "memory(GiB)": 23.83, "elapsed_time": "10m 30s", "remaining_time": "4h 1m 35s", "loss_scale": 1.0, "consumed_samples": 640, "global_step/max_steps": "40/959"} +{"lm loss": 0.81062632, "load_balancing_loss": 1.24373121, "grad_norm": 1.61261022, "learning_rate": 9.38e-06, "elapsed_time_per_iteration": 13.61747928, "memory(GiB)": 23.83, "elapsed_time": "11m 39s", "remaining_time": "3h 56m 37s", "loss_scale": 1.0, "consumed_samples": 720, "global_step/max_steps": "45/959"} +{"lm loss": 0.77504554, "load_balancing_loss": 1.22689133, "grad_norm": 1.47398221, "learning_rate": 1e-05, "elapsed_time_per_iteration": 14.47642145, "memory(GiB)": 23.83, "elapsed_time": "12m 51s", "remaining_time": "3h 53m 43s", "loss_scale": 1.0, "consumed_samples": 800, "global_step/max_steps": "50/959"} +{"lm loss": 0.73532543, "load_balancing_loss": 1.20739851, "grad_norm": 1.23623931, "learning_rate": 1e-05, "elapsed_time_per_iteration": 14.04382567, "memory(GiB)": 23.83, "elapsed_time": "14m 1s", "remaining_time": "3h 50m 32s", "loss_scale": 1.0, "consumed_samples": 880, "global_step/max_steps": "55/959"} +{"lm loss": 0.74113832, "load_balancing_loss": 1.2043664, "grad_norm": 1.50851703, "learning_rate": 1e-05, "elapsed_time_per_iteration": 13.81387239, "memory(GiB)": 23.83, "elapsed_time": "15m 10s", "remaining_time": "3h 47m 25s", "loss_scale": 1.0, "consumed_samples": 960, "global_step/max_steps": "60/959"} +{"lm loss": 0.74582934, "load_balancing_loss": 1.22716551, "grad_norm": 1.15281296, "learning_rate": 9.99e-06, "elapsed_time_per_iteration": 13.28346548, "memory(GiB)": 23.83, "elapsed_time": "16m 17s", "remaining_time": "3h 43m 58s", "loss_scale": 1.0, "consumed_samples": 1040, "global_step/max_steps": "65/959"} +{"lm loss": 0.74203768, "load_balancing_loss": 1.21509628, "grad_norm": 1.056059, "learning_rate": 9.99e-06, "elapsed_time_per_iteration": 14.91785536, "memory(GiB)": 23.83, "elapsed_time": "17m 31s", "remaining_time": "3h 42m 36s", "loss_scale": 1.0, "consumed_samples": 1120, "global_step/max_steps": "70/959"} +{"lm loss": 0.72969427, "load_balancing_loss": 1.20250826, "grad_norm": 1.08561814, "learning_rate": 9.98e-06, "elapsed_time_per_iteration": 13.72953005, "memory(GiB)": 23.83, "elapsed_time": "18m 40s", "remaining_time": "3h 40m 4s", "loss_scale": 1.0, "consumed_samples": 1200, "global_step/max_steps": "75/959"} +{"lm loss": 0.71989145, "load_balancing_loss": 1.23543262, "grad_norm": 1.20314598, "learning_rate": 9.97e-06, "elapsed_time_per_iteration": 13.82676005, "memory(GiB)": 23.83, "elapsed_time": "19m 49s", "remaining_time": "3h 37m 49s", "loss_scale": 1.0, "consumed_samples": 1280, "global_step/max_steps": "80/959"} +{"lm loss": 0.70580616, "load_balancing_loss": 1.22335243, "grad_norm": 0.98150319, "learning_rate": 9.96e-06, "elapsed_time_per_iteration": 14.03268056, "memory(GiB)": 23.83, "elapsed_time": "20m 59s", "remaining_time": "3h 35m 51s", "loss_scale": 1.0, "consumed_samples": 1360, "global_step/max_steps": "85/959"} +{"lm loss": 0.71881227, "load_balancing_loss": 1.22777662, "grad_norm": 1.02965748, "learning_rate": 9.95e-06, "elapsed_time_per_iteration": 13.83492451, "memory(GiB)": 23.84, "elapsed_time": "22m 8s", "remaining_time": "3h 33m 50s", "loss_scale": 1.0, "consumed_samples": 1440, "global_step/max_steps": "90/959"} +{"lm loss": 0.70890021, "load_balancing_loss": 1.21416159, "grad_norm": 1.22099352, "learning_rate": 9.94e-06, "elapsed_time_per_iteration": 13.965798, "memory(GiB)": 23.84, "elapsed_time": "23m 18s", "remaining_time": "3h 32m 0s", "loss_scale": 1.0, "consumed_samples": 1520, "global_step/max_steps": "95/959"} +{"lm loss": 0.7129653, "load_balancing_loss": 1.22133007, "grad_norm": 1.62620473, "learning_rate": 9.93e-06, "elapsed_time_per_iteration": 14.01085343, "memory(GiB)": 23.84, "elapsed_time": "24m 28s", "remaining_time": "3h 30m 16s", "loss_scale": 1.0, "consumed_samples": 1600, "global_step/max_steps": "100/959"} +{"lm loss": 0.7108335, "load_balancing_loss": 1.18576031, "grad_norm": 1.56710112, "learning_rate": 9.91e-06, "elapsed_time_per_iteration": 14.32527709, "memory(GiB)": 23.84, "elapsed_time": "25m 40s", "remaining_time": "3h 28m 47s", "loss_scale": 1.0, "consumed_samples": 1680, "global_step/max_steps": "105/959"} +{"lm loss": 0.71588202, "load_balancing_loss": 1.23983707, "grad_norm": 1.3753103, "learning_rate": 9.9e-06, "elapsed_time_per_iteration": 13.50699635, "memory(GiB)": 23.84, "elapsed_time": "26m 47s", "remaining_time": "3h 26m 49s", "loss_scale": 1.0, "consumed_samples": 1760, "global_step/max_steps": "110/959"} +{"lm loss": 0.70378485, "load_balancing_loss": 1.21246214, "grad_norm": 1.65966737, "learning_rate": 9.88e-06, "elapsed_time_per_iteration": 13.42596173, "memory(GiB)": 23.84, "elapsed_time": "27m 54s", "remaining_time": "3h 24m 52s", "loss_scale": 1.0, "consumed_samples": 1840, "global_step/max_steps": "115/959"} +{"lm loss": 0.71591005, "load_balancing_loss": 1.22506952, "grad_norm": 1.33387232, "learning_rate": 9.86e-06, "elapsed_time_per_iteration": 14.39122243, "memory(GiB)": 23.84, "elapsed_time": "29m 6s", "remaining_time": "3h 23m 33s", "loss_scale": 1.0, "consumed_samples": 1920, "global_step/max_steps": "120/959"} +{"lm loss": 0.70050058, "load_balancing_loss": 1.20918312, "grad_norm": 1.18991506, "learning_rate": 9.84e-06, "elapsed_time_per_iteration": 13.9387176, "memory(GiB)": 23.84, "elapsed_time": "30m 16s", "remaining_time": "3h 22m 0s", "loss_scale": 1.0, "consumed_samples": 2000, "global_step/max_steps": "125/959"} +{"lm loss": 0.71095986, "load_balancing_loss": 1.21849861, "grad_norm": 1.08031464, "learning_rate": 9.82e-06, "elapsed_time_per_iteration": 13.5519815, "memory(GiB)": 23.84, "elapsed_time": "31m 24s", "remaining_time": "3h 20m 16s", "loss_scale": 1.0, "consumed_samples": 2080, "global_step/max_steps": "130/959"} +{"lm loss": 0.69533396, "load_balancing_loss": 1.21670408, "grad_norm": 1.88725471, "learning_rate": 9.8e-06, "elapsed_time_per_iteration": 14.87971225, "memory(GiB)": 23.84, "elapsed_time": "32m 38s", "remaining_time": "3h 19m 15s", "loss_scale": 1.0, "consumed_samples": 2160, "global_step/max_steps": "135/959"} +{"lm loss": 0.69582982, "load_balancing_loss": 1.21480751, "grad_norm": 1.2393949, "learning_rate": 9.78e-06, "elapsed_time_per_iteration": 13.68475585, "memory(GiB)": 23.84, "elapsed_time": "33m 47s", "remaining_time": "3h 17m 39s", "loss_scale": 1.0, "consumed_samples": 2240, "global_step/max_steps": "140/959"} +{"lm loss": 0.72092218, "load_balancing_loss": 1.21764202, "grad_norm": 1.49457455, "learning_rate": 9.75e-06, "elapsed_time_per_iteration": 13.59495277, "memory(GiB)": 23.84, "elapsed_time": "34m 55s", "remaining_time": "3h 16m 1s", "loss_scale": 1.0, "consumed_samples": 2320, "global_step/max_steps": "145/959"} +{"lm loss": 0.71748128, "load_balancing_loss": 1.20876999, "grad_norm": 1.39984107, "learning_rate": 9.72e-06, "elapsed_time_per_iteration": 13.55103006, "memory(GiB)": 23.84, "elapsed_time": "36m 2s", "remaining_time": "3h 14m 25s", "loss_scale": 1.0, "consumed_samples": 2400, "global_step/max_steps": "150/959"} +{"lm loss": 0.70341172, "load_balancing_loss": 1.20885944, "grad_norm": 1.33141994, "learning_rate": 9.7e-06, "elapsed_time_per_iteration": 14.60398636, "memory(GiB)": 23.84, "elapsed_time": "37m 15s", "remaining_time": "3h 13m 18s", "loss_scale": 1.0, "consumed_samples": 2480, "global_step/max_steps": "155/959"} +{"lm loss": 0.68582706, "load_balancing_loss": 1.21731758, "grad_norm": 1.27522469, "learning_rate": 9.67e-06, "elapsed_time_per_iteration": 13.78505235, "memory(GiB)": 23.84, "elapsed_time": "38m 24s", "remaining_time": "3h 11m 50s", "loss_scale": 1.0, "consumed_samples": 2560, "global_step/max_steps": "160/959"} +{"lm loss": 0.69930143, "load_balancing_loss": 1.22104597, "grad_norm": 1.21370447, "learning_rate": 9.64e-06, "elapsed_time_per_iteration": 13.67083073, "memory(GiB)": 23.84, "elapsed_time": "39m 33s", "remaining_time": "3h 10m 20s", "loss_scale": 1.0, "consumed_samples": 2640, "global_step/max_steps": "165/959"} +{"lm loss": 0.70125933, "load_balancing_loss": 1.21435051, "grad_norm": 1.49059439, "learning_rate": 9.61e-06, "elapsed_time_per_iteration": 14.69527059, "memory(GiB)": 26.91, "elapsed_time": "40m 46s", "remaining_time": "3h 9m 15s", "loss_scale": 1.0, "consumed_samples": 2720, "global_step/max_steps": "170/959"} +{"lm loss": 0.67964725, "load_balancing_loss": 1.20746536, "grad_norm": 1.58204508, "learning_rate": 9.57e-06, "elapsed_time_per_iteration": 14.197047, "memory(GiB)": 26.91, "elapsed_time": "41m 57s", "remaining_time": "3h 7m 59s", "loss_scale": 1.0, "consumed_samples": 2800, "global_step/max_steps": "175/959"} +{"lm loss": 0.70567484, "load_balancing_loss": 1.22057285, "grad_norm": 1.26826358, "learning_rate": 9.54e-06, "elapsed_time_per_iteration": 13.44673901, "memory(GiB)": 26.91, "elapsed_time": "43m 4s", "remaining_time": "3h 6m 27s", "loss_scale": 1.0, "consumed_samples": 2880, "global_step/max_steps": "180/959"} +{"lm loss": 0.69657521, "load_balancing_loss": 1.19991426, "grad_norm": 1.36415732, "learning_rate": 9.51e-06, "elapsed_time_per_iteration": 14.6943953, "memory(GiB)": 26.91, "elapsed_time": "44m 18s", "remaining_time": "3h 5m 22s", "loss_scale": 1.0, "consumed_samples": 2960, "global_step/max_steps": "185/959"} +{"lm loss": 0.69118299, "load_balancing_loss": 1.20942593, "grad_norm": 1.80475688, "learning_rate": 9.47e-06, "elapsed_time_per_iteration": 14.04382854, "memory(GiB)": 26.91, "elapsed_time": "45m 28s", "remaining_time": "3h 4m 3s", "loss_scale": 1.0, "consumed_samples": 3040, "global_step/max_steps": "190/959"} +{"lm loss": 0.69597192, "load_balancing_loss": 1.21422796, "grad_norm": 1.47324896, "learning_rate": 9.43e-06, "elapsed_time_per_iteration": 13.68921094, "memory(GiB)": 26.91, "elapsed_time": "46m 37s", "remaining_time": "3h 2m 38s", "loss_scale": 1.0, "consumed_samples": 3120, "global_step/max_steps": "195/959"} +{"lm loss": 0.68303447, "load_balancing_loss": 1.22906342, "grad_norm": 1.3680166, "learning_rate": 9.4e-06, "elapsed_time_per_iteration": 13.52496276, "memory(GiB)": 26.92, "elapsed_time": "47m 44s", "remaining_time": "3h 1m 11s", "loss_scale": 1.0, "consumed_samples": 3200, "global_step/max_steps": "200/959"} +{"lm loss": 0.68806257, "load_balancing_loss": 1.24131298, "grad_norm": 1.56505227, "learning_rate": 9.36e-06, "elapsed_time_per_iteration": 14.2757678, "memory(GiB)": 26.92, "elapsed_time": "48m 56s", "remaining_time": "2h 59m 59s", "loss_scale": 1.0, "consumed_samples": 3280, "global_step/max_steps": "205/959"} +{"lm loss": 0.724967, "load_balancing_loss": 1.22678375, "grad_norm": 1.51439941, "learning_rate": 9.32e-06, "elapsed_time_per_iteration": 13.72586055, "memory(GiB)": 26.92, "elapsed_time": "50m 4s", "remaining_time": "2h 58m 36s", "loss_scale": 1.0, "consumed_samples": 3360, "global_step/max_steps": "210/959"} +{"lm loss": 0.70955911, "load_balancing_loss": 1.20963449, "grad_norm": 4.42585468, "learning_rate": 9.27e-06, "elapsed_time_per_iteration": 13.94133687, "memory(GiB)": 26.92, "elapsed_time": "51m 14s", "remaining_time": "2h 57m 18s", "loss_scale": 1.0, "consumed_samples": 3440, "global_step/max_steps": "215/959"} +{"lm loss": 0.71179538, "load_balancing_loss": 1.20372009, "grad_norm": 1.51301336, "learning_rate": 9.23e-06, "elapsed_time_per_iteration": 14.49882417, "memory(GiB)": 26.92, "elapsed_time": "52m 26s", "remaining_time": "2h 56m 10s", "loss_scale": 1.0, "consumed_samples": 3520, "global_step/max_steps": "220/959"} +{"lm loss": 0.68667197, "load_balancing_loss": 1.21426687, "grad_norm": 1.37935936, "learning_rate": 9.19e-06, "elapsed_time_per_iteration": 13.68668904, "memory(GiB)": 26.92, "elapsed_time": "53m 35s", "remaining_time": "2h 54m 49s", "loss_scale": 1.0, "consumed_samples": 3600, "global_step/max_steps": "225/959"} +{"lm loss": 0.69354124, "load_balancing_loss": 1.20523491, "grad_norm": 1.20044112, "learning_rate": 9.14e-06, "elapsed_time_per_iteration": 14.21179376, "memory(GiB)": 26.92, "elapsed_time": "54m 46s", "remaining_time": "2h 53m 36s", "loss_scale": 1.0, "consumed_samples": 3680, "global_step/max_steps": "230/959"} +{"lm loss": 0.69061613, "load_balancing_loss": 1.21310101, "grad_norm": 1.50078177, "learning_rate": 9.1e-06, "elapsed_time_per_iteration": 14.59870238, "memory(GiB)": 26.92, "elapsed_time": "55m 59s", "remaining_time": "2h 52m 29s", "loss_scale": 1.0, "consumed_samples": 3760, "global_step/max_steps": "235/959"} +{"lm loss": 0.69567351, "load_balancing_loss": 1.21976662, "grad_norm": 1.11827159, "learning_rate": 9.05e-06, "elapsed_time_per_iteration": 13.8904623, "memory(GiB)": 26.92, "elapsed_time": "57m 8s", "remaining_time": "2h 51m 12s", "loss_scale": 1.0, "consumed_samples": 3840, "global_step/max_steps": "240/959"} +{"lm loss": 0.67440906, "load_balancing_loss": 1.2325222, "grad_norm": 1.26940763, "learning_rate": 9e-06, "elapsed_time_per_iteration": 13.82969117, "memory(GiB)": 26.92, "elapsed_time": "58m 17s", "remaining_time": "2h 49m 54s", "loss_scale": 1.0, "consumed_samples": 3920, "global_step/max_steps": "245/959"} +{"lm loss": 0.71276584, "load_balancing_loss": 1.20629129, "grad_norm": 3.176404, "learning_rate": 8.95e-06, "elapsed_time_per_iteration": 13.61757984, "memory(GiB)": 26.92, "elapsed_time": "59m 26s", "remaining_time": "2h 48m 33s", "loss_scale": 1.0, "consumed_samples": 4000, "global_step/max_steps": "250/959"} +{"lm loss": 0.69815464, "load_balancing_loss": 1.2266036, "grad_norm": 1.79611135, "learning_rate": 8.9e-06, "elapsed_time_per_iteration": 14.64853563, "memory(GiB)": 26.92, "elapsed_time": "1h 0m 39s", "remaining_time": "2h 47m 27s", "loss_scale": 1.0, "consumed_samples": 4080, "global_step/max_steps": "255/959"} +{"lm loss": 0.68873558, "load_balancing_loss": 1.21062984, "grad_norm": 1.24560821, "learning_rate": 8.85e-06, "elapsed_time_per_iteration": 13.85480833, "memory(GiB)": 26.92, "elapsed_time": "1h 1m 48s", "remaining_time": "2h 46m 10s", "loss_scale": 1.0, "consumed_samples": 4160, "global_step/max_steps": "260/959"} +{"lm loss": 0.67842588, "load_balancing_loss": 1.20200815, "grad_norm": 1.55584645, "learning_rate": 8.8e-06, "elapsed_time_per_iteration": 13.84869623, "memory(GiB)": 26.92, "elapsed_time": "1h 2m 57s", "remaining_time": "2h 44m 53s", "loss_scale": 1.0, "consumed_samples": 4240, "global_step/max_steps": "265/959"} +{"lm loss": 0.6607408, "load_balancing_loss": 1.22647505, "grad_norm": 1.46516311, "learning_rate": 8.74e-06, "elapsed_time_per_iteration": 14.72152133, "memory(GiB)": 26.92, "elapsed_time": "1h 4m 11s", "remaining_time": "2h 43m 48s", "loss_scale": 1.0, "consumed_samples": 4320, "global_step/max_steps": "270/959"} +{"lm loss": 0.69133501, "load_balancing_loss": 1.21411114, "grad_norm": 1.43080676, "learning_rate": 8.69e-06, "elapsed_time_per_iteration": 13.80062728, "memory(GiB)": 26.92, "elapsed_time": "1h 5m 20s", "remaining_time": "2h 42m 31s", "loss_scale": 1.0, "consumed_samples": 4400, "global_step/max_steps": "275/959"} +{"lm loss": 0.71030383, "load_balancing_loss": 1.23540249, "grad_norm": 1.61090648, "learning_rate": 8.63e-06, "elapsed_time_per_iteration": 13.56823826, "memory(GiB)": 26.92, "elapsed_time": "1h 6m 28s", "remaining_time": "2h 41m 11s", "loss_scale": 1.0, "consumed_samples": 4480, "global_step/max_steps": "280/959"} +{"lm loss": 0.69923334, "load_balancing_loss": 1.20907993, "grad_norm": 2.03609324, "learning_rate": 8.58e-06, "elapsed_time_per_iteration": 14.27589703, "memory(GiB)": 26.92, "elapsed_time": "1h 7m 39s", "remaining_time": "2h 40m 0s", "loss_scale": 1.0, "consumed_samples": 4560, "global_step/max_steps": "285/959"} +{"lm loss": 0.64097362, "load_balancing_loss": 1.19999876, "grad_norm": 6.17119837, "learning_rate": 8.52e-06, "elapsed_time_per_iteration": 14.4095469, "memory(GiB)": 26.92, "elapsed_time": "1h 8m 51s", "remaining_time": "2h 38m 51s", "loss_scale": 1.0, "consumed_samples": 4640, "global_step/max_steps": "290/959"} +{"lm loss": 0.68378825, "load_balancing_loss": 1.20824137, "grad_norm": 1.60843265, "learning_rate": 8.46e-06, "elapsed_time_per_iteration": 14.14937639, "memory(GiB)": 26.92, "elapsed_time": "1h 10m 2s", "remaining_time": "2h 37m 39s", "loss_scale": 1.0, "consumed_samples": 4720, "global_step/max_steps": "295/959"} +{"lm loss": 0.67350702, "load_balancing_loss": 1.22201958, "grad_norm": 1.49810743, "learning_rate": 8.4e-06, "elapsed_time_per_iteration": 13.53796248, "memory(GiB)": 26.92, "elapsed_time": "1h 11m 10s", "remaining_time": "2h 36m 20s", "loss_scale": 1.0, "consumed_samples": 4800, "global_step/max_steps": "300/959"} +{"lm loss": 0.69382176, "load_balancing_loss": 1.21961727, "grad_norm": 1.41956902, "learning_rate": 8.34e-06, "elapsed_time_per_iteration": 14.6765944, "memory(GiB)": 26.92, "elapsed_time": "1h 12m 23s", "remaining_time": "2h 35m 13s", "loss_scale": 1.0, "consumed_samples": 4880, "global_step/max_steps": "305/959"} +{"lm loss": 0.6830905, "load_balancing_loss": 1.20790319, "grad_norm": 1.49527621, "learning_rate": 8.28e-06, "elapsed_time_per_iteration": 13.7998508, "memory(GiB)": 26.92, "elapsed_time": "1h 13m 32s", "remaining_time": "2h 33m 57s", "loss_scale": 1.0, "consumed_samples": 4960, "global_step/max_steps": "310/959"} +{"lm loss": 0.67415442, "load_balancing_loss": 1.18898849, "grad_norm": 1.46815646, "learning_rate": 8.22e-06, "elapsed_time_per_iteration": 14.26142898, "memory(GiB)": 26.92, "elapsed_time": "1h 14m 43s", "remaining_time": "2h 32m 46s", "loss_scale": 1.0, "consumed_samples": 5040, "global_step/max_steps": "315/959"} +{"lm loss": 0.67804279, "load_balancing_loss": 1.20053787, "grad_norm": 1.45099473, "learning_rate": 8.16e-06, "elapsed_time_per_iteration": 14.83761997, "memory(GiB)": 26.92, "elapsed_time": "1h 15m 58s", "remaining_time": "2h 31m 41s", "loss_scale": 1.0, "consumed_samples": 5120, "global_step/max_steps": "320/959"} +{"lm loss": 0.68371248, "load_balancing_loss": 1.2262682, "grad_norm": 1.64987302, "learning_rate": 8.1e-06, "elapsed_time_per_iteration": 13.73906593, "memory(GiB)": 26.92, "elapsed_time": "1h 17m 6s", "remaining_time": "2h 30m 25s", "loss_scale": 1.0, "consumed_samples": 5200, "global_step/max_steps": "325/959"} +{"lm loss": 0.69174333, "load_balancing_loss": 1.21870708, "grad_norm": 1.81273186, "learning_rate": 8.03e-06, "elapsed_time_per_iteration": 13.83182373, "memory(GiB)": 26.92, "elapsed_time": "1h 18m 15s", "remaining_time": "2h 29m 10s", "loss_scale": 1.0, "consumed_samples": 5280, "global_step/max_steps": "330/959"} +{"lm loss": 0.68209887, "load_balancing_loss": 1.20667152, "grad_norm": 1.8218559, "learning_rate": 7.97e-06, "elapsed_time_per_iteration": 14.50589824, "memory(GiB)": 26.92, "elapsed_time": "1h 19m 28s", "remaining_time": "2h 28m 2s", "loss_scale": 1.0, "consumed_samples": 5360, "global_step/max_steps": "335/959"} +{"lm loss": 0.68673735, "load_balancing_loss": 1.19724874, "grad_norm": 1.79535389, "learning_rate": 7.9e-06, "elapsed_time_per_iteration": 14.60847144, "memory(GiB)": 26.92, "elapsed_time": "1h 20m 41s", "remaining_time": "2h 26m 54s", "loss_scale": 1.0, "consumed_samples": 5440, "global_step/max_steps": "340/959"} +{"lm loss": 0.66635518, "load_balancing_loss": 1.21917963, "grad_norm": 1.59678483, "learning_rate": 7.84e-06, "elapsed_time_per_iteration": 13.73251715, "memory(GiB)": 26.92, "elapsed_time": "1h 21m 50s", "remaining_time": "2h 25m 38s", "loss_scale": 1.0, "consumed_samples": 5520, "global_step/max_steps": "345/959"} +{"lm loss": 0.66492872, "load_balancing_loss": 1.20145855, "grad_norm": 1.61781597, "learning_rate": 7.77e-06, "elapsed_time_per_iteration": 13.687953, "memory(GiB)": 26.92, "elapsed_time": "1h 22m 58s", "remaining_time": "2h 24m 22s", "loss_scale": 1.0, "consumed_samples": 5600, "global_step/max_steps": "350/959"} +{"lm loss": 0.67364683, "load_balancing_loss": 1.2197176, "grad_norm": 1.71592295, "learning_rate": 7.7e-06, "elapsed_time_per_iteration": 14.20030303, "memory(GiB)": 26.92, "elapsed_time": "1h 24m 9s", "remaining_time": "2h 23m 11s", "loss_scale": 1.0, "consumed_samples": 5680, "global_step/max_steps": "355/959"} +{"lm loss": 0.68052278, "load_balancing_loss": 1.21344366, "grad_norm": 1.61229646, "learning_rate": 7.64e-06, "elapsed_time_per_iteration": 13.7242414, "memory(GiB)": 26.92, "elapsed_time": "1h 25m 18s", "remaining_time": "2h 21m 56s", "loss_scale": 1.0, "consumed_samples": 5760, "global_step/max_steps": "360/959"} +{"lm loss": 0.69379506, "load_balancing_loss": 1.21055298, "grad_norm": 1.66802633, "learning_rate": 7.57e-06, "elapsed_time_per_iteration": 13.56048899, "memory(GiB)": 26.92, "elapsed_time": "1h 26m 25s", "remaining_time": "2h 20m 39s", "loss_scale": 1.0, "consumed_samples": 5840, "global_step/max_steps": "365/959"} +{"lm loss": 0.67912397, "load_balancing_loss": 1.2061861, "grad_norm": 2.01506925, "learning_rate": 7.5e-06, "elapsed_time_per_iteration": 14.65106931, "memory(GiB)": 26.92, "elapsed_time": "1h 27m 39s", "remaining_time": "2h 19m 32s", "loss_scale": 1.0, "consumed_samples": 5920, "global_step/max_steps": "370/959"} +{"lm loss": 0.69916124, "load_balancing_loss": 1.23439064, "grad_norm": 1.83349979, "learning_rate": 7.43e-06, "elapsed_time_per_iteration": 13.54854441, "memory(GiB)": 26.92, "elapsed_time": "1h 28m 46s", "remaining_time": "2h 18m 15s", "loss_scale": 1.0, "consumed_samples": 6000, "global_step/max_steps": "375/959"} +{"lm loss": 0.66605892, "load_balancing_loss": 1.20368662, "grad_norm": 1.44108832, "learning_rate": 7.36e-06, "elapsed_time_per_iteration": 14.12155619, "memory(GiB)": 26.92, "elapsed_time": "1h 29m 57s", "remaining_time": "2h 17m 4s", "loss_scale": 1.0, "consumed_samples": 6080, "global_step/max_steps": "380/959"} +{"lm loss": 0.66307592, "load_balancing_loss": 1.22158337, "grad_norm": 1.54831707, "learning_rate": 7.29e-06, "elapsed_time_per_iteration": 14.36831193, "memory(GiB)": 26.92, "elapsed_time": "1h 31m 9s", "remaining_time": "2h 15m 54s", "loss_scale": 1.0, "consumed_samples": 6160, "global_step/max_steps": "385/959"} +{"lm loss": 0.67681069, "load_balancing_loss": 1.22311411, "grad_norm": 1.64238691, "learning_rate": 7.22e-06, "elapsed_time_per_iteration": 14.36637979, "memory(GiB)": 26.92, "elapsed_time": "1h 32m 21s", "remaining_time": "2h 14m 44s", "loss_scale": 1.0, "consumed_samples": 6240, "global_step/max_steps": "390/959"} +{"lm loss": 0.67852607, "load_balancing_loss": 1.20636759, "grad_norm": 1.64737213, "learning_rate": 7.14e-06, "elapsed_time_per_iteration": 13.56018333, "memory(GiB)": 26.92, "elapsed_time": "1h 33m 29s", "remaining_time": "2h 13m 28s", "loss_scale": 1.0, "consumed_samples": 6320, "global_step/max_steps": "395/959"} +{"lm loss": 0.66460514, "load_balancing_loss": 1.21333647, "grad_norm": 1.6367867, "learning_rate": 7.07e-06, "elapsed_time_per_iteration": 13.89990273, "memory(GiB)": 26.92, "elapsed_time": "1h 34m 38s", "remaining_time": "2h 12m 15s", "loss_scale": 1.0, "consumed_samples": 6400, "global_step/max_steps": "400/959"} +{"lm loss": 0.68242097, "load_balancing_loss": 1.23139334, "grad_norm": 1.39332163, "learning_rate": 7e-06, "elapsed_time_per_iteration": 14.11065383, "memory(GiB)": 26.92, "elapsed_time": "1h 35m 49s", "remaining_time": "2h 11m 4s", "loss_scale": 1.0, "consumed_samples": 6480, "global_step/max_steps": "405/959"} +{"lm loss": 0.66201429, "load_balancing_loss": 1.21723909, "grad_norm": 2.21418381, "learning_rate": 6.93e-06, "elapsed_time_per_iteration": 13.95836153, "memory(GiB)": 26.92, "elapsed_time": "1h 36m 58s", "remaining_time": "2h 9m 51s", "loss_scale": 1.0, "consumed_samples": 6560, "global_step/max_steps": "410/959"} +{"lm loss": 0.68176627, "load_balancing_loss": 1.20779581, "grad_norm": 1.40026128, "learning_rate": 6.85e-06, "elapsed_time_per_iteration": 13.61587853, "memory(GiB)": 26.92, "elapsed_time": "1h 38m 6s", "remaining_time": "2h 8m 36s", "loss_scale": 1.0, "consumed_samples": 6640, "global_step/max_steps": "415/959"} +{"lm loss": 0.67502904, "load_balancing_loss": 1.21946211, "grad_norm": 1.5953995, "learning_rate": 6.78e-06, "elapsed_time_per_iteration": 14.58641453, "memory(GiB)": 26.92, "elapsed_time": "1h 39m 19s", "remaining_time": "2h 7m 28s", "loss_scale": 1.0, "consumed_samples": 6720, "global_step/max_steps": "420/959"} +{"lm loss": 0.67122431, "load_balancing_loss": 1.21490383, "grad_norm": 1.45291615, "learning_rate": 6.7e-06, "elapsed_time_per_iteration": 14.33995986, "memory(GiB)": 26.92, "elapsed_time": "1h 40m 31s", "remaining_time": "2h 6m 18s", "loss_scale": 1.0, "consumed_samples": 6800, "global_step/max_steps": "425/959"} +{"lm loss": 0.67743855, "load_balancing_loss": 1.20918674, "grad_norm": 1.56858361, "learning_rate": 6.63e-06, "elapsed_time_per_iteration": 13.97433162, "memory(GiB)": 26.92, "elapsed_time": "1h 41m 41s", "remaining_time": "2h 5m 6s", "loss_scale": 1.0, "consumed_samples": 6880, "global_step/max_steps": "430/959"} +{"lm loss": 0.68373375, "load_balancing_loss": 1.20276308, "grad_norm": 2.09396553, "learning_rate": 6.55e-06, "elapsed_time_per_iteration": 13.83750343, "memory(GiB)": 26.92, "elapsed_time": "1h 42m 50s", "remaining_time": "2h 3m 53s", "loss_scale": 1.0, "consumed_samples": 6960, "global_step/max_steps": "435/959"} +{"lm loss": 0.65158515, "load_balancing_loss": 1.19683552, "grad_norm": 2.13931966, "learning_rate": 6.48e-06, "elapsed_time_per_iteration": 14.95207977, "memory(GiB)": 26.92, "elapsed_time": "1h 44m 5s", "remaining_time": "2h 2m 46s", "loss_scale": 1.0, "consumed_samples": 7040, "global_step/max_steps": "440/959"} +{"lm loss": 0.65109324, "load_balancing_loss": 1.19617929, "grad_norm": 1.53346682, "learning_rate": 6.4e-06, "elapsed_time_per_iteration": 13.9185956, "memory(GiB)": 26.92, "elapsed_time": "1h 45m 15s", "remaining_time": "2h 1m 34s", "loss_scale": 1.0, "consumed_samples": 7120, "global_step/max_steps": "445/959"} +{"lm loss": 0.67631788, "load_balancing_loss": 1.2106266, "grad_norm": 1.98323739, "learning_rate": 6.33e-06, "elapsed_time_per_iteration": 13.61535983, "memory(GiB)": 26.92, "elapsed_time": "1h 46m 23s", "remaining_time": "2h 0m 20s", "loss_scale": 1.0, "consumed_samples": 7200, "global_step/max_steps": "450/959"} +{"lm loss": 0.68175831, "load_balancing_loss": 1.20218067, "grad_norm": 1.36305583, "learning_rate": 6.25e-06, "elapsed_time_per_iteration": 14.75067229, "memory(GiB)": 26.92, "elapsed_time": "1h 47m 36s", "remaining_time": "1h 59m 12s", "loss_scale": 1.0, "consumed_samples": 7280, "global_step/max_steps": "455/959"} +{"lm loss": 0.67754254, "load_balancing_loss": 1.21981087, "grad_norm": 2.74955678, "learning_rate": 6.17e-06, "elapsed_time_per_iteration": 14.06981544, "memory(GiB)": 26.92, "elapsed_time": "1h 48m 47s", "remaining_time": "1h 58m 0s", "loss_scale": 1.0, "consumed_samples": 7360, "global_step/max_steps": "460/959"} +{"lm loss": 0.67804451, "load_balancing_loss": 1.22150335, "grad_norm": 2.5690062, "learning_rate": 6.1e-06, "elapsed_time_per_iteration": 13.85553985, "memory(GiB)": 26.92, "elapsed_time": "1h 49m 56s", "remaining_time": "1h 56m 47s", "loss_scale": 1.0, "consumed_samples": 7440, "global_step/max_steps": "465/959"} +{"lm loss": 0.67841511, "load_balancing_loss": 1.22305079, "grad_norm": 1.67029297, "learning_rate": 6.02e-06, "elapsed_time_per_iteration": 14.39890456, "memory(GiB)": 26.92, "elapsed_time": "1h 51m 8s", "remaining_time": "1h 55m 38s", "loss_scale": 1.0, "consumed_samples": 7520, "global_step/max_steps": "470/959"} +{"lm loss": 0.70820785, "load_balancing_loss": 1.21221857, "grad_norm": 2.5150249, "learning_rate": 5.94e-06, "elapsed_time_per_iteration": 14.42393503, "memory(GiB)": 26.92, "elapsed_time": "1h 52m 20s", "remaining_time": "1h 54m 28s", "loss_scale": 1.0, "consumed_samples": 7600, "global_step/max_steps": "475/959"} +{"lm loss": 0.64254103, "load_balancing_loss": 1.20304823, "grad_norm": 1.76451766, "learning_rate": 5.86e-06, "elapsed_time_per_iteration": 14.40587459, "memory(GiB)": 26.92, "elapsed_time": "1h 53m 32s", "remaining_time": "1h 53m 18s", "loss_scale": 1.0, "consumed_samples": 7680, "global_step/max_steps": "480/959"} +{"lm loss": 0.68176947, "load_balancing_loss": 1.21399574, "grad_norm": 1.49693143, "learning_rate": 5.79e-06, "elapsed_time_per_iteration": 14.144066, "memory(GiB)": 26.92, "elapsed_time": "1h 54m 43s", "remaining_time": "1h 52m 7s", "loss_scale": 1.0, "consumed_samples": 7760, "global_step/max_steps": "485/959"} +{"lm loss": 0.67010074, "load_balancing_loss": 1.20861759, "grad_norm": 1.43718874, "learning_rate": 5.71e-06, "elapsed_time_per_iteration": 14.20793791, "memory(GiB)": 26.92, "elapsed_time": "1h 55m 54s", "remaining_time": "1h 50m 56s", "loss_scale": 1.0, "consumed_samples": 7840, "global_step/max_steps": "490/959"} +{"lm loss": 0.65236111, "load_balancing_loss": 1.21000557, "grad_norm": 1.79839027, "learning_rate": 5.63e-06, "elapsed_time_per_iteration": 14.17679467, "memory(GiB)": 26.92, "elapsed_time": "1h 57m 5s", "remaining_time": "1h 49m 45s", "loss_scale": 1.0, "consumed_samples": 7920, "global_step/max_steps": "495/959"} +{"lm loss": 0.67274723, "load_balancing_loss": 1.21431999, "grad_norm": 2.27496481, "learning_rate": 5.55e-06, "elapsed_time_per_iteration": 13.98319654, "memory(GiB)": 26.92, "elapsed_time": "1h 58m 15s", "remaining_time": "1h 48m 33s", "loss_scale": 1.0, "consumed_samples": 8000, "global_step/max_steps": "500/959"} +{"lm loss": 0.67200074, "load_balancing_loss": 1.19712601, "grad_norm": 1.6934613, "learning_rate": 5.48e-06, "elapsed_time_per_iteration": 14.62192121, "memory(GiB)": 26.92, "elapsed_time": "1h 59m 28s", "remaining_time": "1h 47m 24s", "loss_scale": 1.0, "consumed_samples": 8080, "global_step/max_steps": "505/959"} +{"lm loss": 0.68272018, "load_balancing_loss": 1.2068346, "grad_norm": 1.93739533, "learning_rate": 5.4e-06, "elapsed_time_per_iteration": 14.04652395, "memory(GiB)": 26.92, "elapsed_time": "2h 0m 38s", "remaining_time": "1h 46m 12s", "loss_scale": 1.0, "consumed_samples": 8160, "global_step/max_steps": "510/959"} +{"lm loss": 0.67799749, "load_balancing_loss": 1.20584631, "grad_norm": 1.64505589, "learning_rate": 5.32e-06, "elapsed_time_per_iteration": 13.7925694, "memory(GiB)": 26.92, "elapsed_time": "2h 1m 47s", "remaining_time": "1h 45m 0s", "loss_scale": 1.0, "consumed_samples": 8240, "global_step/max_steps": "515/959"} +{"lm loss": 0.63443904, "load_balancing_loss": 1.21174583, "grad_norm": 1.87587929, "learning_rate": 5.24e-06, "elapsed_time_per_iteration": 14.32158456, "memory(GiB)": 26.92, "elapsed_time": "2h 2m 59s", "remaining_time": "1h 43m 49s", "loss_scale": 1.0, "consumed_samples": 8320, "global_step/max_steps": "520/959"} +{"lm loss": 0.63735619, "load_balancing_loss": 1.20214405, "grad_norm": 1.92017424, "learning_rate": 5.17e-06, "elapsed_time_per_iteration": 13.99936147, "memory(GiB)": 26.92, "elapsed_time": "2h 4m 9s", "remaining_time": "1h 42m 37s", "loss_scale": 1.0, "consumed_samples": 8400, "global_step/max_steps": "525/959"} +{"lm loss": 0.66667976, "load_balancing_loss": 1.22804604, "grad_norm": 1.85430849, "learning_rate": 5.09e-06, "elapsed_time_per_iteration": 13.46915231, "memory(GiB)": 26.92, "elapsed_time": "2h 5m 16s", "remaining_time": "1h 41m 24s", "loss_scale": 1.0, "consumed_samples": 8480, "global_step/max_steps": "530/959"} +{"lm loss": 0.68244848, "load_balancing_loss": 1.2323103, "grad_norm": 1.91672814, "learning_rate": 5.01e-06, "elapsed_time_per_iteration": 13.98815475, "memory(GiB)": 26.92, "elapsed_time": "2h 6m 26s", "remaining_time": "1h 40m 12s", "loss_scale": 1.0, "consumed_samples": 8560, "global_step/max_steps": "535/959"} +{"lm loss": 0.67595878, "load_balancing_loss": 1.21930933, "grad_norm": 2.47050309, "learning_rate": 4.93e-06, "elapsed_time_per_iteration": 14.49671683, "memory(GiB)": 30.08, "elapsed_time": "2h 7m 38s", "remaining_time": "1h 39m 2s", "loss_scale": 1.0, "consumed_samples": 8640, "global_step/max_steps": "540/959"} +{"lm loss": 0.68730936, "load_balancing_loss": 1.21157398, "grad_norm": 1.9231652, "learning_rate": 4.86e-06, "elapsed_time_per_iteration": 13.72432842, "memory(GiB)": 30.08, "elapsed_time": "2h 8m 47s", "remaining_time": "1h 37m 50s", "loss_scale": 1.0, "consumed_samples": 8720, "global_step/max_steps": "545/959"} +{"lm loss": 0.66914902, "load_balancing_loss": 1.2313324, "grad_norm": 1.94407725, "learning_rate": 4.78e-06, "elapsed_time_per_iteration": 13.59542851, "memory(GiB)": 30.08, "elapsed_time": "2h 9m 55s", "remaining_time": "1h 36m 36s", "loss_scale": 1.0, "consumed_samples": 8800, "global_step/max_steps": "550/959"} +{"lm loss": 0.65865746, "load_balancing_loss": 1.20956192, "grad_norm": 1.72185886, "learning_rate": 4.7e-06, "elapsed_time_per_iteration": 14.62540517, "memory(GiB)": 30.08, "elapsed_time": "2h 11m 8s", "remaining_time": "1h 35m 27s", "loss_scale": 1.0, "consumed_samples": 8880, "global_step/max_steps": "555/959"} +{"lm loss": 0.65881333, "load_balancing_loss": 1.19655151, "grad_norm": 1.6928848, "learning_rate": 4.63e-06, "elapsed_time_per_iteration": 14.11795468, "memory(GiB)": 30.08, "elapsed_time": "2h 12m 19s", "remaining_time": "1h 34m 16s", "loss_scale": 1.0, "consumed_samples": 8960, "global_step/max_steps": "560/959"} +{"lm loss": 0.66557999, "load_balancing_loss": 1.22354279, "grad_norm": 1.98559964, "learning_rate": 4.55e-06, "elapsed_time_per_iteration": 13.80524249, "memory(GiB)": 30.08, "elapsed_time": "2h 13m 28s", "remaining_time": "1h 33m 4s", "loss_scale": 1.0, "consumed_samples": 9040, "global_step/max_steps": "565/959"} +{"lm loss": 0.66747971, "load_balancing_loss": 1.2082243, "grad_norm": 1.63904464, "learning_rate": 4.48e-06, "elapsed_time_per_iteration": 14.13489695, "memory(GiB)": 30.08, "elapsed_time": "2h 14m 38s", "remaining_time": "1h 31m 53s", "loss_scale": 1.0, "consumed_samples": 9120, "global_step/max_steps": "570/959"} +{"lm loss": 0.67499123, "load_balancing_loss": 1.2171526, "grad_norm": 2.42798209, "learning_rate": 4.4e-06, "elapsed_time_per_iteration": 14.41892204, "memory(GiB)": 30.08, "elapsed_time": "2h 15m 50s", "remaining_time": "1h 30m 43s", "loss_scale": 1.0, "consumed_samples": 9200, "global_step/max_steps": "575/959"} +{"lm loss": 0.62815189, "load_balancing_loss": 1.19988117, "grad_norm": 1.87352943, "learning_rate": 4.33e-06, "elapsed_time_per_iteration": 14.12666035, "memory(GiB)": 30.08, "elapsed_time": "2h 17m 1s", "remaining_time": "1h 29m 32s", "loss_scale": 1.0, "consumed_samples": 9280, "global_step/max_steps": "580/959"} +{"lm loss": 0.6740777, "load_balancing_loss": 1.20913258, "grad_norm": 3.52269173, "learning_rate": 4.25e-06, "elapsed_time_per_iteration": 14.18904381, "memory(GiB)": 30.08, "elapsed_time": "2h 18m 12s", "remaining_time": "1h 28m 21s", "loss_scale": 1.0, "consumed_samples": 9360, "global_step/max_steps": "585/959"} +{"lm loss": 0.67889557, "load_balancing_loss": 1.23486786, "grad_norm": 1.73121047, "learning_rate": 4.18e-06, "elapsed_time_per_iteration": 14.15841317, "memory(GiB)": 30.08, "elapsed_time": "2h 19m 23s", "remaining_time": "1h 27m 10s", "loss_scale": 1.0, "consumed_samples": 9440, "global_step/max_steps": "590/959"} +{"lm loss": 0.65817795, "load_balancing_loss": 1.19870834, "grad_norm": 1.81982124, "learning_rate": 4.1e-06, "elapsed_time_per_iteration": 14.15320802, "memory(GiB)": 30.08, "elapsed_time": "2h 20m 34s", "remaining_time": "1h 25m 59s", "loss_scale": 1.0, "consumed_samples": 9520, "global_step/max_steps": "595/959"} +{"lm loss": 0.67751765, "load_balancing_loss": 1.18990307, "grad_norm": 2.08861804, "learning_rate": 4.03e-06, "elapsed_time_per_iteration": 14.30246496, "memory(GiB)": 30.08, "elapsed_time": "2h 21m 45s", "remaining_time": "1h 24m 49s", "loss_scale": 1.0, "consumed_samples": 9600, "global_step/max_steps": "600/959"} +{"lm loss": 0.66621227, "load_balancing_loss": 1.22363129, "grad_norm": 1.72245872, "learning_rate": 3.96e-06, "elapsed_time_per_iteration": 14.10831404, "memory(GiB)": 30.08, "elapsed_time": "2h 22m 56s", "remaining_time": "1h 23m 38s", "loss_scale": 1.0, "consumed_samples": 9680, "global_step/max_steps": "605/959"} +{"lm loss": 0.66751232, "load_balancing_loss": 1.20470686, "grad_norm": 1.58105874, "learning_rate": 3.88e-06, "elapsed_time_per_iteration": 14.17582479, "memory(GiB)": 30.08, "elapsed_time": "2h 24m 7s", "remaining_time": "1h 22m 27s", "loss_scale": 1.0, "consumed_samples": 9760, "global_step/max_steps": "610/959"} +{"lm loss": 0.64563975, "load_balancing_loss": 1.19483013, "grad_norm": 3.18904066, "learning_rate": 3.81e-06, "elapsed_time_per_iteration": 13.92049627, "memory(GiB)": 30.08, "elapsed_time": "2h 25m 16s", "remaining_time": "1h 21m 15s", "loss_scale": 1.0, "consumed_samples": 9840, "global_step/max_steps": "615/959"} +{"lm loss": 0.67731533, "load_balancing_loss": 1.23271513, "grad_norm": 2.73926401, "learning_rate": 3.74e-06, "elapsed_time_per_iteration": 14.0555584, "memory(GiB)": 30.08, "elapsed_time": "2h 26m 26s", "remaining_time": "1h 20m 4s", "loss_scale": 1.0, "consumed_samples": 9920, "global_step/max_steps": "620/959"} +{"lm loss": 0.65157347, "load_balancing_loss": 1.21175194, "grad_norm": 2.40440631, "learning_rate": 3.67e-06, "elapsed_time_per_iteration": 14.29558601, "memory(GiB)": 30.08, "elapsed_time": "2h 27m 38s", "remaining_time": "1h 18m 53s", "loss_scale": 1.0, "consumed_samples": 10000, "global_step/max_steps": "625/959"} +{"lm loss": 0.66868024, "load_balancing_loss": 1.21082516, "grad_norm": 1.74617672, "learning_rate": 3.6e-06, "elapsed_time_per_iteration": 14.06684823, "memory(GiB)": 30.08, "elapsed_time": "2h 28m 48s", "remaining_time": "1h 17m 42s", "loss_scale": 1.0, "consumed_samples": 10080, "global_step/max_steps": "630/959"} +{"lm loss": 0.63749228, "load_balancing_loss": 1.23136826, "grad_norm": 4.58653116, "learning_rate": 3.53e-06, "elapsed_time_per_iteration": 13.54445534, "memory(GiB)": 30.08, "elapsed_time": "2h 29m 56s", "remaining_time": "1h 16m 30s", "loss_scale": 1.0, "consumed_samples": 10160, "global_step/max_steps": "635/959"} +{"lm loss": 0.63531365, "load_balancing_loss": 1.21312466, "grad_norm": 1.56398833, "learning_rate": 3.46e-06, "elapsed_time_per_iteration": 14.2878561, "memory(GiB)": 30.08, "elapsed_time": "2h 31m 7s", "remaining_time": "1h 15m 19s", "loss_scale": 1.0, "consumed_samples": 10240, "global_step/max_steps": "640/959"} +{"lm loss": 0.68465762, "load_balancing_loss": 1.20650349, "grad_norm": 1.62420523, "learning_rate": 3.39e-06, "elapsed_time_per_iteration": 14.26957817, "memory(GiB)": 30.08, "elapsed_time": "2h 32m 19s", "remaining_time": "1h 14m 9s", "loss_scale": 1.0, "consumed_samples": 10320, "global_step/max_steps": "645/959"} +{"lm loss": 0.66761332, "load_balancing_loss": 1.20740423, "grad_norm": 5.04033041, "learning_rate": 3.32e-06, "elapsed_time_per_iteration": 13.95026436, "memory(GiB)": 30.08, "elapsed_time": "2h 33m 29s", "remaining_time": "1h 12m 57s", "loss_scale": 1.0, "consumed_samples": 10400, "global_step/max_steps": "650/959"} +{"lm loss": 0.64910007, "load_balancing_loss": 1.21883907, "grad_norm": 1.79608369, "learning_rate": 3.25e-06, "elapsed_time_per_iteration": 14.63971596, "memory(GiB)": 30.08, "elapsed_time": "2h 34m 42s", "remaining_time": "1h 11m 48s", "loss_scale": 1.0, "consumed_samples": 10480, "global_step/max_steps": "655/959"} +{"lm loss": 0.65699739, "load_balancing_loss": 1.21239166, "grad_norm": 1.87016571, "learning_rate": 3.19e-06, "elapsed_time_per_iteration": 14.16772714, "memory(GiB)": 30.08, "elapsed_time": "2h 35m 53s", "remaining_time": "1h 10m 37s", "loss_scale": 1.0, "consumed_samples": 10560, "global_step/max_steps": "660/959"} +{"lm loss": 0.64574237, "load_balancing_loss": 1.20562572, "grad_norm": 2.75039983, "learning_rate": 3.12e-06, "elapsed_time_per_iteration": 14.0241776, "memory(GiB)": 30.08, "elapsed_time": "2h 37m 3s", "remaining_time": "1h 9m 26s", "loss_scale": 1.0, "consumed_samples": 10640, "global_step/max_steps": "665/959"} +{"lm loss": 0.66599016, "load_balancing_loss": 1.20989838, "grad_norm": 2.24021435, "learning_rate": 3.06e-06, "elapsed_time_per_iteration": 14.22016792, "memory(GiB)": 30.08, "elapsed_time": "2h 38m 14s", "remaining_time": "1h 8m 15s", "loss_scale": 1.0, "consumed_samples": 10720, "global_step/max_steps": "670/959"} +{"lm loss": 0.64244137, "load_balancing_loss": 1.20823269, "grad_norm": 2.31592941, "learning_rate": 2.99e-06, "elapsed_time_per_iteration": 14.16020274, "memory(GiB)": 30.08, "elapsed_time": "2h 39m 25s", "remaining_time": "1h 7m 4s", "loss_scale": 1.0, "consumed_samples": 10800, "global_step/max_steps": "675/959"} +{"lm loss": 0.64508114, "load_balancing_loss": 1.21357927, "grad_norm": 2.9052031, "learning_rate": 2.93e-06, "elapsed_time_per_iteration": 13.93161001, "memory(GiB)": 30.08, "elapsed_time": "2h 40m 34s", "remaining_time": "1h 5m 53s", "loss_scale": 1.0, "consumed_samples": 10880, "global_step/max_steps": "680/959"} +{"lm loss": 0.66267586, "load_balancing_loss": 1.2208334, "grad_norm": 2.02677131, "learning_rate": 2.86e-06, "elapsed_time_per_iteration": 14.14775062, "memory(GiB)": 30.08, "elapsed_time": "2h 41m 45s", "remaining_time": "1h 4m 42s", "loss_scale": 1.0, "consumed_samples": 10960, "global_step/max_steps": "685/959"} +{"lm loss": 0.64519243, "load_balancing_loss": 1.20855532, "grad_norm": 1.86924994, "learning_rate": 2.8e-06, "elapsed_time_per_iteration": 14.33208928, "memory(GiB)": 30.08, "elapsed_time": "2h 42m 57s", "remaining_time": "1h 3m 31s", "loss_scale": 1.0, "consumed_samples": 11040, "global_step/max_steps": "690/959"} +{"lm loss": 0.68504992, "load_balancing_loss": 1.20972881, "grad_norm": 1.65998971, "learning_rate": 2.74e-06, "elapsed_time_per_iteration": 13.92105331, "memory(GiB)": 30.08, "elapsed_time": "2h 44m 6s", "remaining_time": "1h 2m 20s", "loss_scale": 1.0, "consumed_samples": 11120, "global_step/max_steps": "695/959"} +{"lm loss": 0.66511049, "load_balancing_loss": 1.21427202, "grad_norm": 1.84007406, "learning_rate": 2.68e-06, "elapsed_time_per_iteration": 13.4261807, "memory(GiB)": 30.08, "elapsed_time": "2h 45m 13s", "remaining_time": "1h 1m 8s", "loss_scale": 1.0, "consumed_samples": 11200, "global_step/max_steps": "700/959"} +{"lm loss": 0.66611891, "load_balancing_loss": 1.22220669, "grad_norm": 2.2070508, "learning_rate": 2.62e-06, "elapsed_time_per_iteration": 14.55913548, "memory(GiB)": 30.08, "elapsed_time": "2h 46m 26s", "remaining_time": "59m 58s", "loss_scale": 1.0, "consumed_samples": 11280, "global_step/max_steps": "705/959"} +{"lm loss": 0.64956689, "load_balancing_loss": 1.21518154, "grad_norm": 1.75219178, "learning_rate": 2.56e-06, "elapsed_time_per_iteration": 13.96889133, "memory(GiB)": 30.08, "elapsed_time": "2h 47m 36s", "remaining_time": "58m 46s", "loss_scale": 1.0, "consumed_samples": 11360, "global_step/max_steps": "710/959"} +{"lm loss": 0.66015544, "load_balancing_loss": 1.21894617, "grad_norm": 2.39603376, "learning_rate": 2.5e-06, "elapsed_time_per_iteration": 13.87261744, "memory(GiB)": 30.08, "elapsed_time": "2h 48m 45s", "remaining_time": "57m 35s", "loss_scale": 1.0, "consumed_samples": 11440, "global_step/max_steps": "715/959"} +{"lm loss": 0.66658978, "load_balancing_loss": 1.24279118, "grad_norm": 1.54583776, "learning_rate": 2.44e-06, "elapsed_time_per_iteration": 14.23206387, "memory(GiB)": 30.08, "elapsed_time": "2h 49m 57s", "remaining_time": "56m 24s", "loss_scale": 1.0, "consumed_samples": 11520, "global_step/max_steps": "720/959"} +{"lm loss": 0.65649023, "load_balancing_loss": 1.20888653, "grad_norm": 2.47591519, "learning_rate": 2.39e-06, "elapsed_time_per_iteration": 14.53944983, "memory(GiB)": 30.08, "elapsed_time": "2h 51m 9s", "remaining_time": "55m 14s", "loss_scale": 1.0, "consumed_samples": 11600, "global_step/max_steps": "725/959"} +{"lm loss": 0.6551753, "load_balancing_loss": 1.20419731, "grad_norm": 2.32404184, "learning_rate": 2.33e-06, "elapsed_time_per_iteration": 14.15087953, "memory(GiB)": 30.08, "elapsed_time": "2h 52m 20s", "remaining_time": "54m 3s", "loss_scale": 1.0, "consumed_samples": 11680, "global_step/max_steps": "730/959"} +{"lm loss": 0.64416866, "load_balancing_loss": 1.19961624, "grad_norm": 2.0516386, "learning_rate": 2.28e-06, "elapsed_time_per_iteration": 14.00865092, "memory(GiB)": 30.08, "elapsed_time": "2h 53m 30s", "remaining_time": "52m 52s", "loss_scale": 1.0, "consumed_samples": 11760, "global_step/max_steps": "735/959"} +{"lm loss": 0.69017496, "load_balancing_loss": 1.23317556, "grad_norm": 1.7816987, "learning_rate": 2.22e-06, "elapsed_time_per_iteration": 13.91983161, "memory(GiB)": 30.08, "elapsed_time": "2h 54m 40s", "remaining_time": "51m 41s", "loss_scale": 1.0, "consumed_samples": 11840, "global_step/max_steps": "740/959"} +{"lm loss": 0.66721888, "load_balancing_loss": 1.22994556, "grad_norm": 1.55712533, "learning_rate": 2.17e-06, "elapsed_time_per_iteration": 13.96247864, "memory(GiB)": 30.08, "elapsed_time": "2h 55m 49s", "remaining_time": "50m 30s", "loss_scale": 1.0, "consumed_samples": 11920, "global_step/max_steps": "745/959"} +{"lm loss": 0.64800005, "load_balancing_loss": 1.20349846, "grad_norm": 2.49920535, "learning_rate": 2.12e-06, "elapsed_time_per_iteration": 14.29613628, "memory(GiB)": 30.08, "elapsed_time": "2h 57m 1s", "remaining_time": "49m 19s", "loss_scale": 1.0, "consumed_samples": 12000, "global_step/max_steps": "750/959"} +{"lm loss": 0.6937645, "load_balancing_loss": 1.1980628, "grad_norm": 1.97100401, "learning_rate": 2.07e-06, "elapsed_time_per_iteration": 14.22938309, "memory(GiB)": 30.08, "elapsed_time": "2h 58m 12s", "remaining_time": "48m 9s", "loss_scale": 1.0, "consumed_samples": 12080, "global_step/max_steps": "755/959"} +{"lm loss": 0.6467205, "load_balancing_loss": 1.22211046, "grad_norm": 2.29735541, "learning_rate": 2.02e-06, "elapsed_time_per_iteration": 14.12293062, "memory(GiB)": 30.08, "elapsed_time": "2h 59m 23s", "remaining_time": "46m 58s", "loss_scale": 1.0, "consumed_samples": 12160, "global_step/max_steps": "760/959"} +{"lm loss": 0.66573315, "load_balancing_loss": 1.23537521, "grad_norm": 1.84771502, "learning_rate": 1.97e-06, "elapsed_time_per_iteration": 13.98618116, "memory(GiB)": 30.08, "elapsed_time": "3h 0m 33s", "remaining_time": "45m 47s", "loss_scale": 1.0, "consumed_samples": 12240, "global_step/max_steps": "765/959"} +{"lm loss": 0.67220392, "load_balancing_loss": 1.2058671, "grad_norm": 2.1829524, "learning_rate": 1.92e-06, "elapsed_time_per_iteration": 13.75660162, "memory(GiB)": 30.08, "elapsed_time": "3h 1m 41s", "remaining_time": "44m 35s", "loss_scale": 1.0, "consumed_samples": 12320, "global_step/max_steps": "770/959"} +{"lm loss": 0.66221509, "load_balancing_loss": 1.24808855, "grad_norm": 1.89107132, "learning_rate": 1.88e-06, "elapsed_time_per_iteration": 14.28494515, "memory(GiB)": 30.08, "elapsed_time": "3h 2m 53s", "remaining_time": "43m 25s", "loss_scale": 1.0, "consumed_samples": 12400, "global_step/max_steps": "775/959"} +{"lm loss": 0.66308436, "load_balancing_loss": 1.23306255, "grad_norm": 2.3307085, "learning_rate": 1.83e-06, "elapsed_time_per_iteration": 13.87595668, "memory(GiB)": 30.08, "elapsed_time": "3h 4m 2s", "remaining_time": "42m 14s", "loss_scale": 1.0, "consumed_samples": 12480, "global_step/max_steps": "780/959"} +{"lm loss": 2.06886578, "load_balancing_loss": 1.20992255, "grad_norm": 10.24282837, "learning_rate": 2.1e-07, "elapsed_time_per_iteration": 63.71238828, "memory(GiB)": 17.94, "elapsed_time": "1m 3s", "remaining_time": "16h 57m 16s", "loss_scale": 1.0, "consumed_samples": 16, "global_step/max_steps": "1/959"} +{"lm loss": 1.92957091, "load_balancing_loss": 1.20491993, "grad_norm": 9.86786842, "learning_rate": 1.04e-06, "elapsed_time_per_iteration": 14.58304673, "memory(GiB)": 18.01, "elapsed_time": "2m 2s", "remaining_time": "6h 28m 6s", "loss_scale": 1.0, "consumed_samples": 80, "global_step/max_steps": "5/959"} +{"lm loss": 1.93814259, "load_balancing_loss": 1.21117668, "grad_norm": 10.71291924, "learning_rate": 2.09e-06, "elapsed_time_per_iteration": 13.36452332, "memory(GiB)": 18.03, "elapsed_time": "3m 8s", "remaining_time": "4h 58m 43s", "loss_scale": 1.0, "consumed_samples": 160, "global_step/max_steps": "10/959"} +{"lm loss": 1.89382992, "load_balancing_loss": 1.21492052, "grad_norm": 10.62137413, "learning_rate": 3.13e-06, "elapsed_time_per_iteration": 13.52114959, "memory(GiB)": 18.04, "elapsed_time": "4m 16s", "remaining_time": "4h 29m 0s", "loss_scale": 1.0, "consumed_samples": 240, "global_step/max_steps": "15/959"} +{"lm loss": 1.82503052, "load_balancing_loss": 1.19523335, "grad_norm": 9.48527241, "learning_rate": 4.17e-06, "elapsed_time_per_iteration": 13.82691803, "memory(GiB)": 18.04, "elapsed_time": "5m 25s", "remaining_time": "4h 14m 47s", "loss_scale": 1.0, "consumed_samples": 320, "global_step/max_steps": "20/959"} +{"lm loss": 1.67277164, "load_balancing_loss": 1.22121458, "grad_norm": 9.04932499, "learning_rate": 5.21e-06, "elapsed_time_per_iteration": 12.7452405, "memory(GiB)": 20.83, "elapsed_time": "6m 29s", "remaining_time": "4h 2m 25s", "loss_scale": 1.0, "consumed_samples": 400, "global_step/max_steps": "25/959"} +{"lm loss": 1.40562696, "load_balancing_loss": 1.22925444, "grad_norm": 7.18562794, "learning_rate": 6.26e-06, "elapsed_time_per_iteration": 12.88511834, "memory(GiB)": 20.83, "elapsed_time": "7m 33s", "remaining_time": "3h 54m 11s", "loss_scale": 1.0, "consumed_samples": 480, "global_step/max_steps": "30/959"} +{"lm loss": 1.11568928, "load_balancing_loss": 1.1989706, "grad_norm": 5.20824385, "learning_rate": 7.3e-06, "elapsed_time_per_iteration": 13.70730891, "memory(GiB)": 23.82, "elapsed_time": "8m 42s", "remaining_time": "3h 49m 48s", "loss_scale": 1.0, "consumed_samples": 560, "global_step/max_steps": "35/959"} +{"lm loss": 0.92254686, "load_balancing_loss": 1.20485973, "grad_norm": 3.69306636, "learning_rate": 8.34e-06, "elapsed_time_per_iteration": 13.3900362, "memory(GiB)": 23.82, "elapsed_time": "9m 49s", "remaining_time": "3h 45m 37s", "loss_scale": 1.0, "consumed_samples": 640, "global_step/max_steps": "40/959"} +{"lm loss": 0.81015253, "load_balancing_loss": 1.24363976, "grad_norm": 1.32440484, "learning_rate": 9.38e-06, "elapsed_time_per_iteration": 12.88515096, "memory(GiB)": 23.82, "elapsed_time": "10m 53s", "remaining_time": "3h 41m 16s", "loss_scale": 1.0, "consumed_samples": 720, "global_step/max_steps": "45/959"} +{"lm loss": 0.77407823, "load_balancing_loss": 1.22693901, "grad_norm": 1.3291651, "learning_rate": 1e-05, "elapsed_time_per_iteration": 13.34316936, "memory(GiB)": 23.82, "elapsed_time": "12m 0s", "remaining_time": "3h 38m 16s", "loss_scale": 1.0, "consumed_samples": 800, "global_step/max_steps": "50/959"} +{"lm loss": 0.7323154, "load_balancing_loss": 1.20724592, "grad_norm": 1.29250658, "learning_rate": 1e-05, "elapsed_time_per_iteration": 13.6047152, "memory(GiB)": 23.82, "elapsed_time": "13m 8s", "remaining_time": "3h 35m 58s", "loss_scale": 1.0, "consumed_samples": 880, "global_step/max_steps": "55/959"} +{"lm loss": 0.73894773, "load_balancing_loss": 1.20417271, "grad_norm": 1.44008648, "learning_rate": 1e-05, "elapsed_time_per_iteration": 13.06575303, "memory(GiB)": 23.83, "elapsed_time": "14m 13s", "remaining_time": "3h 33m 11s", "loss_scale": 1.0, "consumed_samples": 960, "global_step/max_steps": "60/959"} +{"lm loss": 0.74643235, "load_balancing_loss": 1.22730465, "grad_norm": 1.1885401, "learning_rate": 9.99e-06, "elapsed_time_per_iteration": 12.56520724, "memory(GiB)": 23.83, "elapsed_time": "15m 16s", "remaining_time": "3h 30m 6s", "loss_scale": 1.0, "consumed_samples": 1040, "global_step/max_steps": "65/959"} +{"lm loss": 0.74425449, "load_balancing_loss": 1.21515703, "grad_norm": 1.11474264, "learning_rate": 9.99e-06, "elapsed_time_per_iteration": 14.13530898, "memory(GiB)": 23.83, "elapsed_time": "16m 27s", "remaining_time": "3h 28m 57s", "loss_scale": 1.0, "consumed_samples": 1120, "global_step/max_steps": "70/959"} +{"lm loss": 0.72742648, "load_balancing_loss": 1.20234861, "grad_norm": 1.09064591, "learning_rate": 9.98e-06, "elapsed_time_per_iteration": 12.9369441, "memory(GiB)": 23.83, "elapsed_time": "17m 31s", "remaining_time": "3h 26m 38s", "loss_scale": 1.0, "consumed_samples": 1200, "global_step/max_steps": "75/959"} +{"lm loss": 0.72376757, "load_balancing_loss": 1.23565903, "grad_norm": 1.2204566, "learning_rate": 9.97e-06, "elapsed_time_per_iteration": 12.98535366, "memory(GiB)": 23.83, "elapsed_time": "18m 36s", "remaining_time": "3h 24m 31s", "loss_scale": 1.0, "consumed_samples": 1280, "global_step/max_steps": "80/959"} +{"lm loss": 0.7017756, "load_balancing_loss": 1.22313681, "grad_norm": 1.10794389, "learning_rate": 9.96e-06, "elapsed_time_per_iteration": 13.42102551, "memory(GiB)": 23.83, "elapsed_time": "19m 43s", "remaining_time": "3h 22m 53s", "loss_scale": 1.0, "consumed_samples": 1360, "global_step/max_steps": "85/959"} +{"lm loss": 0.71977625, "load_balancing_loss": 1.22693224, "grad_norm": 1.0200212, "learning_rate": 9.95e-06, "elapsed_time_per_iteration": 12.81575251, "memory(GiB)": 23.83, "elapsed_time": "20m 48s", "remaining_time": "3h 20m 50s", "loss_scale": 1.0, "consumed_samples": 1440, "global_step/max_steps": "90/959"} +{"lm loss": 0.71113863, "load_balancing_loss": 1.21309967, "grad_norm": 1.26112986, "learning_rate": 9.94e-06, "elapsed_time_per_iteration": 12.973035, "memory(GiB)": 23.83, "elapsed_time": "21m 52s", "remaining_time": "3h 19m 0s", "loss_scale": 1.0, "consumed_samples": 1520, "global_step/max_steps": "95/959"} +{"lm loss": 0.72005372, "load_balancing_loss": 1.21990709, "grad_norm": 1.74891996, "learning_rate": 9.93e-06, "elapsed_time_per_iteration": 13.10345984, "memory(GiB)": 23.83, "elapsed_time": "22m 58s", "remaining_time": "3h 17m 20s", "loss_scale": 1.0, "consumed_samples": 1600, "global_step/max_steps": "100/959"} +{"lm loss": 0.71399546, "load_balancing_loss": 1.18470812, "grad_norm": 1.61752319, "learning_rate": 9.91e-06, "elapsed_time_per_iteration": 14.12296462, "memory(GiB)": 23.83, "elapsed_time": "24m 9s", "remaining_time": "3h 16m 25s", "loss_scale": 1.0, "consumed_samples": 1680, "global_step/max_steps": "105/959"} +{"lm loss": 0.71406131, "load_balancing_loss": 1.23845196, "grad_norm": 1.49773681, "learning_rate": 9.9e-06, "elapsed_time_per_iteration": 12.62372222, "memory(GiB)": 23.83, "elapsed_time": "25m 12s", "remaining_time": "3h 14m 31s", "loss_scale": 1.0, "consumed_samples": 1760, "global_step/max_steps": "110/959"} +{"lm loss": 0.70218997, "load_balancing_loss": 1.21150827, "grad_norm": 1.39957273, "learning_rate": 9.88e-06, "elapsed_time_per_iteration": 12.54999404, "memory(GiB)": 23.83, "elapsed_time": "26m 14s", "remaining_time": "3h 12m 38s", "loss_scale": 1.0, "consumed_samples": 1840, "global_step/max_steps": "115/959"} +{"lm loss": 0.71337457, "load_balancing_loss": 1.22423391, "grad_norm": 1.57530069, "learning_rate": 9.86e-06, "elapsed_time_per_iteration": 13.54683132, "memory(GiB)": 23.83, "elapsed_time": "27m 22s", "remaining_time": "3h 11m 24s", "loss_scale": 1.0, "consumed_samples": 1920, "global_step/max_steps": "120/959"} +{"lm loss": 0.70388231, "load_balancing_loss": 1.20859489, "grad_norm": 1.22586584, "learning_rate": 9.84e-06, "elapsed_time_per_iteration": 13.03826308, "memory(GiB)": 23.83, "elapsed_time": "28m 27s", "remaining_time": "3h 9m 54s", "loss_scale": 1.0, "consumed_samples": 2000, "global_step/max_steps": "125/959"} +{"lm loss": 0.70792499, "load_balancing_loss": 1.21837025, "grad_norm": 1.03551054, "learning_rate": 9.82e-06, "elapsed_time_per_iteration": 12.6396544, "memory(GiB)": 23.83, "elapsed_time": "29m 31s", "remaining_time": "3h 8m 13s", "loss_scale": 1.0, "consumed_samples": 2080, "global_step/max_steps": "130/959"} +{"lm loss": 0.69626551, "load_balancing_loss": 1.21686602, "grad_norm": 1.40769327, "learning_rate": 9.8e-06, "elapsed_time_per_iteration": 13.56857266, "memory(GiB)": 23.83, "elapsed_time": "30m 38s", "remaining_time": "3h 7m 3s", "loss_scale": 1.0, "consumed_samples": 2160, "global_step/max_steps": "135/959"} +{"lm loss": 0.69571896, "load_balancing_loss": 1.21517315, "grad_norm": 1.63471723, "learning_rate": 9.78e-06, "elapsed_time_per_iteration": 12.82136669, "memory(GiB)": 23.83, "elapsed_time": "31m 42s", "remaining_time": "3h 5m 32s", "loss_scale": 1.0, "consumed_samples": 2240, "global_step/max_steps": "140/959"} +{"lm loss": 0.71157146, "load_balancing_loss": 1.21809635, "grad_norm": 1.56176901, "learning_rate": 9.75e-06, "elapsed_time_per_iteration": 12.74295664, "memory(GiB)": 23.84, "elapsed_time": "32m 46s", "remaining_time": "3h 4m 0s", "loss_scale": 1.0, "consumed_samples": 2320, "global_step/max_steps": "145/959"} +{"lm loss": 0.71846275, "load_balancing_loss": 1.20912418, "grad_norm": 1.36546957, "learning_rate": 9.72e-06, "elapsed_time_per_iteration": 12.69672127, "memory(GiB)": 23.84, "elapsed_time": "33m 50s", "remaining_time": "3h 2m 29s", "loss_scale": 1.0, "consumed_samples": 2400, "global_step/max_steps": "150/959"} +{"lm loss": 0.70332475, "load_balancing_loss": 1.20964556, "grad_norm": 1.40407336, "learning_rate": 9.7e-06, "elapsed_time_per_iteration": 13.43944569, "memory(GiB)": 23.84, "elapsed_time": "34m 57s", "remaining_time": "3h 1m 19s", "loss_scale": 1.0, "consumed_samples": 2480, "global_step/max_steps": "155/959"} +{"lm loss": 0.68306885, "load_balancing_loss": 1.21869965, "grad_norm": 1.39606726, "learning_rate": 9.67e-06, "elapsed_time_per_iteration": 12.83301344, "memory(GiB)": 23.84, "elapsed_time": "36m 1s", "remaining_time": "2h 59m 54s", "loss_scale": 1.0, "consumed_samples": 2560, "global_step/max_steps": "160/959"} +{"lm loss": 0.70048528, "load_balancing_loss": 1.22217169, "grad_norm": 1.30130267, "learning_rate": 9.64e-06, "elapsed_time_per_iteration": 12.71054006, "memory(GiB)": 23.84, "elapsed_time": "37m 5s", "remaining_time": "2h 58m 27s", "loss_scale": 1.0, "consumed_samples": 2640, "global_step/max_steps": "165/959"} +{"lm loss": 0.70725036, "load_balancing_loss": 1.21582775, "grad_norm": 1.07638848, "learning_rate": 9.61e-06, "elapsed_time_per_iteration": 13.65557408, "memory(GiB)": 26.91, "elapsed_time": "38m 13s", "remaining_time": "2h 57m 23s", "loss_scale": 1.0, "consumed_samples": 2720, "global_step/max_steps": "170/959"} +{"lm loss": 0.67854166, "load_balancing_loss": 1.2088995, "grad_norm": 1.44063139, "learning_rate": 9.57e-06, "elapsed_time_per_iteration": 13.22497873, "memory(GiB)": 26.91, "elapsed_time": "39m 19s", "remaining_time": "2h 56m 10s", "loss_scale": 1.0, "consumed_samples": 2800, "global_step/max_steps": "175/959"} +{"lm loss": 0.70242591, "load_balancing_loss": 1.22202606, "grad_norm": 1.28942323, "learning_rate": 9.54e-06, "elapsed_time_per_iteration": 12.52396946, "memory(GiB)": 26.91, "elapsed_time": "40m 22s", "remaining_time": "2h 54m 42s", "loss_scale": 1.0, "consumed_samples": 2880, "global_step/max_steps": "180/959"} +{"lm loss": 0.69823046, "load_balancing_loss": 1.20110226, "grad_norm": 1.36896193, "learning_rate": 9.51e-06, "elapsed_time_per_iteration": 13.88461313, "memory(GiB)": 26.91, "elapsed_time": "41m 31s", "remaining_time": "2h 53m 44s", "loss_scale": 1.0, "consumed_samples": 2960, "global_step/max_steps": "185/959"} +{"lm loss": 0.69642968, "load_balancing_loss": 1.21070881, "grad_norm": 1.56397939, "learning_rate": 9.47e-06, "elapsed_time_per_iteration": 13.03471971, "memory(GiB)": 26.91, "elapsed_time": "42m 36s", "remaining_time": "2h 52m 27s", "loss_scale": 1.0, "consumed_samples": 3040, "global_step/max_steps": "190/959"} +{"lm loss": 0.69341106, "load_balancing_loss": 1.21546421, "grad_norm": 1.68351007, "learning_rate": 9.43e-06, "elapsed_time_per_iteration": 12.8994947, "memory(GiB)": 26.91, "elapsed_time": "43m 41s", "remaining_time": "2h 51m 9s", "loss_scale": 1.0, "consumed_samples": 3120, "global_step/max_steps": "195/959"} +{"lm loss": 0.68506241, "load_balancing_loss": 1.2301342, "grad_norm": 1.29981375, "learning_rate": 9.4e-06, "elapsed_time_per_iteration": 13.35933871, "memory(GiB)": 26.92, "elapsed_time": "44m 48s", "remaining_time": "2h 50m 0s", "loss_scale": 1.0, "consumed_samples": 3200, "global_step/max_steps": "200/959"} +{"lm loss": 0.68732257, "load_balancing_loss": 1.24294367, "grad_norm": 1.558429, "learning_rate": 9.36e-06, "elapsed_time_per_iteration": 12.81425571, "memory(GiB)": 26.92, "elapsed_time": "45m 52s", "remaining_time": "2h 48m 42s", "loss_scale": 1.0, "consumed_samples": 3280, "global_step/max_steps": "205/959"} +{"lm loss": 0.71940861, "load_balancing_loss": 1.22853107, "grad_norm": 1.43521667, "learning_rate": 9.32e-06, "elapsed_time_per_iteration": 12.82522125, "memory(GiB)": 26.92, "elapsed_time": "46m 56s", "remaining_time": "2h 47m 24s", "loss_scale": 1.0, "consumed_samples": 3360, "global_step/max_steps": "210/959"} +{"lm loss": 0.71197515, "load_balancing_loss": 1.2111062, "grad_norm": 1.46772563, "learning_rate": 9.27e-06, "elapsed_time_per_iteration": 13.30652823, "memory(GiB)": 26.92, "elapsed_time": "48m 2s", "remaining_time": "2h 46m 15s", "loss_scale": 1.0, "consumed_samples": 3440, "global_step/max_steps": "215/959"} +{"lm loss": 0.71488962, "load_balancing_loss": 1.20489912, "grad_norm": 1.33897734, "learning_rate": 9.23e-06, "elapsed_time_per_iteration": 13.42528701, "memory(GiB)": 26.92, "elapsed_time": "49m 9s", "remaining_time": "2h 45m 8s", "loss_scale": 1.0, "consumed_samples": 3520, "global_step/max_steps": "220/959"} +{"lm loss": 0.68779602, "load_balancing_loss": 1.21626902, "grad_norm": 1.31285572, "learning_rate": 9.19e-06, "elapsed_time_per_iteration": 12.7779151, "memory(GiB)": 26.92, "elapsed_time": "50m 13s", "remaining_time": "2h 43m 51s", "loss_scale": 1.0, "consumed_samples": 3600, "global_step/max_steps": "225/959"} +{"lm loss": 0.69062428, "load_balancing_loss": 1.20778332, "grad_norm": 1.1497997, "learning_rate": 9.14e-06, "elapsed_time_per_iteration": 13.38974843, "memory(GiB)": 26.92, "elapsed_time": "51m 20s", "remaining_time": "2h 42m 44s", "loss_scale": 1.0, "consumed_samples": 3680, "global_step/max_steps": "230/959"} +{"lm loss": 0.69345603, "load_balancing_loss": 1.21642504, "grad_norm": 1.74396288, "learning_rate": 9.1e-06, "elapsed_time_per_iteration": 13.79105287, "memory(GiB)": 26.92, "elapsed_time": "52m 29s", "remaining_time": "2h 41m 43s", "loss_scale": 1.0, "consumed_samples": 3760, "global_step/max_steps": "235/959"} +{"lm loss": 0.69400005, "load_balancing_loss": 1.22231197, "grad_norm": 1.60233974, "learning_rate": 9.05e-06, "elapsed_time_per_iteration": 13.01223683, "memory(GiB)": 26.92, "elapsed_time": "53m 34s", "remaining_time": "2h 40m 30s", "loss_scale": 1.0, "consumed_samples": 3840, "global_step/max_steps": "240/959"} +{"lm loss": 0.67433553, "load_balancing_loss": 1.23650646, "grad_norm": 1.34954321, "learning_rate": 9e-06, "elapsed_time_per_iteration": 13.12311487, "memory(GiB)": 26.92, "elapsed_time": "54m 40s", "remaining_time": "2h 39m 19s", "loss_scale": 1.0, "consumed_samples": 3920, "global_step/max_steps": "245/959"} +{"lm loss": 0.71407199, "load_balancing_loss": 1.20926914, "grad_norm": 1.78911996, "learning_rate": 8.95e-06, "elapsed_time_per_iteration": 13.76540356, "memory(GiB)": 26.92, "elapsed_time": "55m 49s", "remaining_time": "2h 38m 18s", "loss_scale": 1.0, "consumed_samples": 4000, "global_step/max_steps": "250/959"} +{"lm loss": 0.69453945, "load_balancing_loss": 1.22994947, "grad_norm": 1.44316745, "learning_rate": 8.9e-06, "elapsed_time_per_iteration": 13.23981814, "memory(GiB)": 26.92, "elapsed_time": "56m 55s", "remaining_time": "2h 37m 9s", "loss_scale": 1.0, "consumed_samples": 4080, "global_step/max_steps": "255/959"} +{"lm loss": 0.69443078, "load_balancing_loss": 1.21392984, "grad_norm": 1.38425231, "learning_rate": 8.85e-06, "elapsed_time_per_iteration": 13.12964129, "memory(GiB)": 26.92, "elapsed_time": "58m 1s", "remaining_time": "2h 35m 58s", "loss_scale": 1.0, "consumed_samples": 4160, "global_step/max_steps": "260/959"} +{"lm loss": 0.67764521, "load_balancing_loss": 1.20495005, "grad_norm": 1.29763007, "learning_rate": 8.8e-06, "elapsed_time_per_iteration": 13.58978081, "memory(GiB)": 26.92, "elapsed_time": "59m 8s", "remaining_time": "2h 34m 54s", "loss_scale": 1.0, "consumed_samples": 4240, "global_step/max_steps": "265/959"} +{"lm loss": 0.66261258, "load_balancing_loss": 1.22952204, "grad_norm": 1.36466217, "learning_rate": 8.74e-06, "elapsed_time_per_iteration": 13.73256478, "memory(GiB)": 26.92, "elapsed_time": "1h 0m 17s", "remaining_time": "2h 33m 51s", "loss_scale": 1.0, "consumed_samples": 4320, "global_step/max_steps": "270/959"} +{"lm loss": 0.69376264, "load_balancing_loss": 1.21690302, "grad_norm": 1.47674739, "learning_rate": 8.69e-06, "elapsed_time_per_iteration": 13.11170807, "memory(GiB)": 26.92, "elapsed_time": "1h 1m 23s", "remaining_time": "2h 32m 41s", "loss_scale": 1.0, "consumed_samples": 4400, "global_step/max_steps": "275/959"} +{"lm loss": 0.70969791, "load_balancing_loss": 1.23821278, "grad_norm": 1.61364341, "learning_rate": 8.63e-06, "elapsed_time_per_iteration": 13.19372921, "memory(GiB)": 26.92, "elapsed_time": "1h 2m 29s", "remaining_time": "2h 31m 31s", "loss_scale": 1.0, "consumed_samples": 4480, "global_step/max_steps": "280/959"} +{"lm loss": 0.69223571, "load_balancing_loss": 1.2115037, "grad_norm": 1.71168387, "learning_rate": 8.58e-06, "elapsed_time_per_iteration": 13.72757664, "memory(GiB)": 26.92, "elapsed_time": "1h 3m 37s", "remaining_time": "2h 30m 28s", "loss_scale": 1.0, "consumed_samples": 4560, "global_step/max_steps": "285/959"} +{"lm loss": 0.63861847, "load_balancing_loss": 1.20224609, "grad_norm": 1.55486059, "learning_rate": 8.52e-06, "elapsed_time_per_iteration": 13.33420477, "memory(GiB)": 26.92, "elapsed_time": "1h 4m 44s", "remaining_time": "2h 29m 21s", "loss_scale": 1.0, "consumed_samples": 4640, "global_step/max_steps": "290/959"} +{"lm loss": 0.68385267, "load_balancing_loss": 1.21085377, "grad_norm": 1.46925437, "learning_rate": 8.46e-06, "elapsed_time_per_iteration": 13.3752202, "memory(GiB)": 26.92, "elapsed_time": "1h 5m 51s", "remaining_time": "2h 28m 13s", "loss_scale": 1.0, "consumed_samples": 4720, "global_step/max_steps": "295/959"} +{"lm loss": 0.67873311, "load_balancing_loss": 1.22453403, "grad_norm": 1.54380488, "learning_rate": 8.4e-06, "elapsed_time_per_iteration": 13.5942368, "memory(GiB)": 26.92, "elapsed_time": "1h 6m 59s", "remaining_time": "2h 27m 9s", "loss_scale": 1.0, "consumed_samples": 4800, "global_step/max_steps": "300/959"} +{"lm loss": 0.70681133, "load_balancing_loss": 1.22228737, "grad_norm": 3.27423716, "learning_rate": 8.34e-06, "elapsed_time_per_iteration": 13.40735507, "memory(GiB)": 26.92, "elapsed_time": "1h 8m 6s", "remaining_time": "2h 26m 2s", "loss_scale": 1.0, "consumed_samples": 4880, "global_step/max_steps": "305/959"} +{"lm loss": 0.6785531, "load_balancing_loss": 1.20997486, "grad_norm": 1.39119625, "learning_rate": 8.28e-06, "elapsed_time_per_iteration": 13.04447551, "memory(GiB)": 26.92, "elapsed_time": "1h 9m 11s", "remaining_time": "2h 24m 51s", "loss_scale": 1.0, "consumed_samples": 4960, "global_step/max_steps": "310/959"} +{"lm loss": 0.67058353, "load_balancing_loss": 1.19075346, "grad_norm": 1.51892519, "learning_rate": 8.22e-06, "elapsed_time_per_iteration": 13.84959316, "memory(GiB)": 26.92, "elapsed_time": "1h 10m 20s", "remaining_time": "2h 23m 49s", "loss_scale": 1.0, "consumed_samples": 5040, "global_step/max_steps": "315/959"} +{"lm loss": 0.67872586, "load_balancing_loss": 1.20207367, "grad_norm": 1.57388735, "learning_rate": 8.16e-06, "elapsed_time_per_iteration": 13.68481083, "memory(GiB)": 26.92, "elapsed_time": "1h 11m 29s", "remaining_time": "2h 22m 45s", "loss_scale": 1.0, "consumed_samples": 5120, "global_step/max_steps": "320/959"} +{"lm loss": 0.68498526, "load_balancing_loss": 1.22752342, "grad_norm": 1.9876436, "learning_rate": 8.1e-06, "elapsed_time_per_iteration": 12.84689474, "memory(GiB)": 26.92, "elapsed_time": "1h 12m 33s", "remaining_time": "2h 21m 32s", "loss_scale": 1.0, "consumed_samples": 5200, "global_step/max_steps": "325/959"} +{"lm loss": 0.69300127, "load_balancing_loss": 1.21988487, "grad_norm": 1.8384186, "learning_rate": 8.03e-06, "elapsed_time_per_iteration": 13.51344695, "memory(GiB)": 26.92, "elapsed_time": "1h 13m 41s", "remaining_time": "2h 20m 26s", "loss_scale": 1.0, "consumed_samples": 5280, "global_step/max_steps": "330/959"} +{"lm loss": 0.68107185, "load_balancing_loss": 1.20786743, "grad_norm": 1.84077263, "learning_rate": 7.97e-06, "elapsed_time_per_iteration": 13.78666272, "memory(GiB)": 26.92, "elapsed_time": "1h 14m 49s", "remaining_time": "2h 19m 23s", "loss_scale": 1.0, "consumed_samples": 5360, "global_step/max_steps": "335/959"} +{"lm loss": 0.68505297, "load_balancing_loss": 1.19855213, "grad_norm": 1.78402913, "learning_rate": 7.9e-06, "elapsed_time_per_iteration": 13.27343254, "memory(GiB)": 26.92, "elapsed_time": "1h 15m 56s", "remaining_time": "2h 18m 15s", "loss_scale": 1.0, "consumed_samples": 5440, "global_step/max_steps": "340/959"} +{"lm loss": 0.66926761, "load_balancing_loss": 1.2210516, "grad_norm": 1.43754649, "learning_rate": 7.84e-06, "elapsed_time_per_iteration": 13.00520086, "memory(GiB)": 26.92, "elapsed_time": "1h 17m 1s", "remaining_time": "2h 17m 4s", "loss_scale": 1.0, "consumed_samples": 5520, "global_step/max_steps": "345/959"} +{"lm loss": 0.66539259, "load_balancing_loss": 1.2034853, "grad_norm": 5.70521688, "learning_rate": 7.77e-06, "elapsed_time_per_iteration": 13.70043683, "memory(GiB)": 26.92, "elapsed_time": "1h 18m 9s", "remaining_time": "2h 16m 0s", "loss_scale": 1.0, "consumed_samples": 5600, "global_step/max_steps": "350/959"} +{"lm loss": 0.67914996, "load_balancing_loss": 1.22239695, "grad_norm": 2.97913885, "learning_rate": 7.7e-06, "elapsed_time_per_iteration": 12.93355064, "memory(GiB)": 26.92, "elapsed_time": "1h 19m 14s", "remaining_time": "2h 14m 49s", "loss_scale": 1.0, "consumed_samples": 5680, "global_step/max_steps": "355/959"} +{"lm loss": 0.68032794, "load_balancing_loss": 1.21620121, "grad_norm": 1.61384642, "learning_rate": 7.64e-06, "elapsed_time_per_iteration": 12.76316328, "memory(GiB)": 26.92, "elapsed_time": "1h 20m 18s", "remaining_time": "2h 13m 37s", "loss_scale": 1.0, "consumed_samples": 5760, "global_step/max_steps": "360/959"} +{"lm loss": 0.69513245, "load_balancing_loss": 1.21358213, "grad_norm": 1.57571542, "learning_rate": 7.57e-06, "elapsed_time_per_iteration": 13.36024928, "memory(GiB)": 26.92, "elapsed_time": "1h 21m 25s", "remaining_time": "2h 12m 30s", "loss_scale": 1.0, "consumed_samples": 5840, "global_step/max_steps": "365/959"} +{"lm loss": 0.68256378, "load_balancing_loss": 1.2093771, "grad_norm": 2.57815361, "learning_rate": 7.5e-06, "elapsed_time_per_iteration": 13.54159961, "memory(GiB)": 26.92, "elapsed_time": "1h 22m 32s", "remaining_time": "2h 11m 24s", "loss_scale": 1.0, "consumed_samples": 5920, "global_step/max_steps": "370/959"} +{"lm loss": 0.70180597, "load_balancing_loss": 1.23810673, "grad_norm": 2.05379844, "learning_rate": 7.43e-06, "elapsed_time_per_iteration": 12.6224597, "memory(GiB)": 26.92, "elapsed_time": "1h 23m 35s", "remaining_time": "2h 10m 11s", "loss_scale": 1.0, "consumed_samples": 6000, "global_step/max_steps": "375/959"} +{"lm loss": 0.67485328, "load_balancing_loss": 1.20716352, "grad_norm": 1.50011325, "learning_rate": 7.36e-06, "elapsed_time_per_iteration": 13.71890941, "memory(GiB)": 26.92, "elapsed_time": "1h 24m 44s", "remaining_time": "2h 9m 7s", "loss_scale": 1.0, "consumed_samples": 6080, "global_step/max_steps": "380/959"} +{"lm loss": 0.6586813, "load_balancing_loss": 1.22574863, "grad_norm": 1.35998273, "learning_rate": 7.29e-06, "elapsed_time_per_iteration": 13.81637907, "memory(GiB)": 26.92, "elapsed_time": "1h 25m 53s", "remaining_time": "2h 8m 3s", "loss_scale": 1.0, "consumed_samples": 6160, "global_step/max_steps": "385/959"} +{"lm loss": 0.67549467, "load_balancing_loss": 1.22760391, "grad_norm": 1.5517714, "learning_rate": 7.22e-06, "elapsed_time_per_iteration": 12.92212448, "memory(GiB)": 26.92, "elapsed_time": "1h 26m 58s", "remaining_time": "2h 6m 53s", "loss_scale": 1.0, "consumed_samples": 6240, "global_step/max_steps": "390/959"} +{"lm loss": 0.68373966, "load_balancing_loss": 1.2104454, "grad_norm": 1.88438511, "learning_rate": 7.14e-06, "elapsed_time_per_iteration": 12.96343985, "memory(GiB)": 26.92, "elapsed_time": "1h 28m 3s", "remaining_time": "2h 5m 43s", "loss_scale": 1.0, "consumed_samples": 6320, "global_step/max_steps": "395/959"} +{"lm loss": 0.66267271, "load_balancing_loss": 1.21717224, "grad_norm": 2.58585644, "learning_rate": 7.07e-06, "elapsed_time_per_iteration": 13.43087559, "memory(GiB)": 26.92, "elapsed_time": "1h 29m 10s", "remaining_time": "2h 4m 36s", "loss_scale": 1.0, "consumed_samples": 6400, "global_step/max_steps": "400/959"} +{"lm loss": 0.6852057, "load_balancing_loss": 1.23560762, "grad_norm": 1.60448372, "learning_rate": 7e-06, "elapsed_time_per_iteration": 12.98602638, "memory(GiB)": 26.92, "elapsed_time": "1h 30m 15s", "remaining_time": "2h 3m 27s", "loss_scale": 1.0, "consumed_samples": 6480, "global_step/max_steps": "405/959"} +{"lm loss": 0.66286182, "load_balancing_loss": 1.22133522, "grad_norm": 2.2380302, "learning_rate": 6.93e-06, "elapsed_time_per_iteration": 12.95461979, "memory(GiB)": 26.92, "elapsed_time": "1h 31m 19s", "remaining_time": "2h 2m 17s", "loss_scale": 1.0, "consumed_samples": 6560, "global_step/max_steps": "410/959"} +{"lm loss": 0.67819147, "load_balancing_loss": 1.21105633, "grad_norm": 1.50214314, "learning_rate": 6.85e-06, "elapsed_time_per_iteration": 13.4435823, "memory(GiB)": 26.92, "elapsed_time": "1h 32m 27s", "remaining_time": "2h 1m 11s", "loss_scale": 1.0, "consumed_samples": 6640, "global_step/max_steps": "415/959"} +{"lm loss": 0.66779718, "load_balancing_loss": 1.22320175, "grad_norm": 3.00486946, "learning_rate": 6.78e-06, "elapsed_time_per_iteration": 13.45641313, "memory(GiB)": 26.92, "elapsed_time": "1h 33m 34s", "remaining_time": "2h 0m 5s", "loss_scale": 1.0, "consumed_samples": 6720, "global_step/max_steps": "420/959"} +{"lm loss": 0.67349768, "load_balancing_loss": 1.21832151, "grad_norm": 1.49953067, "learning_rate": 6.7e-06, "elapsed_time_per_iteration": 13.03734803, "memory(GiB)": 26.92, "elapsed_time": "1h 34m 39s", "remaining_time": "1h 58m 56s", "loss_scale": 1.0, "consumed_samples": 6800, "global_step/max_steps": "425/959"} +{"lm loss": 0.67636366, "load_balancing_loss": 1.21261215, "grad_norm": 1.91162455, "learning_rate": 6.63e-06, "elapsed_time_per_iteration": 13.84785242, "memory(GiB)": 26.92, "elapsed_time": "1h 35m 48s", "remaining_time": "1h 57m 52s", "loss_scale": 1.0, "consumed_samples": 6880, "global_step/max_steps": "430/959"} +{"lm loss": 0.6808948, "load_balancing_loss": 1.20604153, "grad_norm": 2.01189709, "learning_rate": 6.55e-06, "elapsed_time_per_iteration": 14.22545052, "memory(GiB)": 26.92, "elapsed_time": "1h 36m 59s", "remaining_time": "1h 56m 50s", "loss_scale": 1.0, "consumed_samples": 6960, "global_step/max_steps": "435/959"} +{"lm loss": 0.65666513, "load_balancing_loss": 1.20060768, "grad_norm": 1.98876238, "learning_rate": 6.48e-06, "elapsed_time_per_iteration": 13.72553029, "memory(GiB)": 26.92, "elapsed_time": "1h 38m 8s", "remaining_time": "1h 55m 45s", "loss_scale": 1.0, "consumed_samples": 7040, "global_step/max_steps": "440/959"} +{"lm loss": 0.65942221, "load_balancing_loss": 1.20034781, "grad_norm": 1.58260036, "learning_rate": 6.4e-06, "elapsed_time_per_iteration": 13.39227767, "memory(GiB)": 26.92, "elapsed_time": "1h 39m 15s", "remaining_time": "1h 54m 39s", "loss_scale": 1.0, "consumed_samples": 7120, "global_step/max_steps": "445/959"} +{"lm loss": 0.67702065, "load_balancing_loss": 1.21444721, "grad_norm": 9.02685547, "learning_rate": 6.33e-06, "elapsed_time_per_iteration": 13.10408626, "memory(GiB)": 26.92, "elapsed_time": "1h 40m 21s", "remaining_time": "1h 53m 30s", "loss_scale": 1.0, "consumed_samples": 7200, "global_step/max_steps": "450/959"} +{"lm loss": 0.68576007, "load_balancing_loss": 1.20540628, "grad_norm": 1.55608356, "learning_rate": 6.25e-06, "elapsed_time_per_iteration": 13.49795728, "memory(GiB)": 26.92, "elapsed_time": "1h 41m 28s", "remaining_time": "1h 52m 24s", "loss_scale": 1.0, "consumed_samples": 7280, "global_step/max_steps": "455/959"} +{"lm loss": 0.6805738, "load_balancing_loss": 1.22336397, "grad_norm": 3.5316534, "learning_rate": 6.17e-06, "elapsed_time_per_iteration": 13.17884068, "memory(GiB)": 26.92, "elapsed_time": "1h 42m 34s", "remaining_time": "1h 51m 16s", "loss_scale": 1.0, "consumed_samples": 7360, "global_step/max_steps": "460/959"} +{"lm loss": 0.68322296, "load_balancing_loss": 1.22495518, "grad_norm": 2.33962059, "learning_rate": 6.1e-06, "elapsed_time_per_iteration": 13.51972585, "memory(GiB)": 26.92, "elapsed_time": "1h 43m 42s", "remaining_time": "1h 50m 10s", "loss_scale": 1.0, "consumed_samples": 7440, "global_step/max_steps": "465/959"} +{"lm loss": 0.68087111, "load_balancing_loss": 1.22664785, "grad_norm": 1.62873173, "learning_rate": 6.02e-06, "elapsed_time_per_iteration": 13.44696321, "memory(GiB)": 26.92, "elapsed_time": "1h 44m 49s", "remaining_time": "1h 49m 3s", "loss_scale": 1.0, "consumed_samples": 7520, "global_step/max_steps": "470/959"} +{"lm loss": 0.70930552, "load_balancing_loss": 1.21460981, "grad_norm": 1.72264457, "learning_rate": 5.94e-06, "elapsed_time_per_iteration": 13.2267354, "memory(GiB)": 26.92, "elapsed_time": "1h 45m 55s", "remaining_time": "1h 47m 55s", "loss_scale": 1.0, "consumed_samples": 7600, "global_step/max_steps": "475/959"} +{"lm loss": 0.63959198, "load_balancing_loss": 1.2055109, "grad_norm": 2.12124777, "learning_rate": 5.86e-06, "elapsed_time_per_iteration": 13.89485841, "memory(GiB)": 26.92, "elapsed_time": "1h 47m 4s", "remaining_time": "1h 46m 51s", "loss_scale": 1.0, "consumed_samples": 7680, "global_step/max_steps": "480/959"} +{"lm loss": 0.67656569, "load_balancing_loss": 1.21644163, "grad_norm": 1.69146919, "learning_rate": 5.79e-06, "elapsed_time_per_iteration": 13.59690862, "memory(GiB)": 26.92, "elapsed_time": "1h 48m 12s", "remaining_time": "1h 45m 45s", "loss_scale": 1.0, "consumed_samples": 7760, "global_step/max_steps": "485/959"} +{"lm loss": 0.67077231, "load_balancing_loss": 1.21081591, "grad_norm": 1.41808224, "learning_rate": 5.71e-06, "elapsed_time_per_iteration": 12.78219166, "memory(GiB)": 26.92, "elapsed_time": "1h 49m 16s", "remaining_time": "1h 44m 35s", "loss_scale": 1.0, "consumed_samples": 7840, "global_step/max_steps": "490/959"} +{"lm loss": 0.64368477, "load_balancing_loss": 1.21199551, "grad_norm": 1.71637428, "learning_rate": 5.63e-06, "elapsed_time_per_iteration": 13.40105319, "memory(GiB)": 26.92, "elapsed_time": "1h 50m 23s", "remaining_time": "1h 43m 28s", "loss_scale": 1.0, "consumed_samples": 7920, "global_step/max_steps": "495/959"} +{"lm loss": 0.67234874, "load_balancing_loss": 1.21613035, "grad_norm": 2.26565242, "learning_rate": 5.55e-06, "elapsed_time_per_iteration": 13.42510633, "memory(GiB)": 26.92, "elapsed_time": "1h 51m 30s", "remaining_time": "1h 42m 22s", "loss_scale": 1.0, "consumed_samples": 8000, "global_step/max_steps": "500/959"} +{"lm loss": 0.66411633, "load_balancing_loss": 1.19840355, "grad_norm": 1.90876031, "learning_rate": 5.48e-06, "elapsed_time_per_iteration": 13.36393523, "memory(GiB)": 26.92, "elapsed_time": "1h 52m 37s", "remaining_time": "1h 41m 15s", "loss_scale": 1.0, "consumed_samples": 8080, "global_step/max_steps": "505/959"} +{"lm loss": 0.6757484, "load_balancing_loss": 1.20758343, "grad_norm": 1.54890227, "learning_rate": 5.4e-06, "elapsed_time_per_iteration": 13.16775298, "memory(GiB)": 26.92, "elapsed_time": "1h 53m 43s", "remaining_time": "1h 40m 7s", "loss_scale": 1.0, "consumed_samples": 8160, "global_step/max_steps": "510/959"} +{"lm loss": 0.68052797, "load_balancing_loss": 1.206674, "grad_norm": 1.69060194, "learning_rate": 5.32e-06, "elapsed_time_per_iteration": 13.22219591, "memory(GiB)": 26.92, "elapsed_time": "1h 54m 49s", "remaining_time": "1h 38m 59s", "loss_scale": 1.0, "consumed_samples": 8240, "global_step/max_steps": "515/959"} +{"lm loss": 0.63512077, "load_balancing_loss": 1.21249657, "grad_norm": 1.86370623, "learning_rate": 5.24e-06, "elapsed_time_per_iteration": 13.31823168, "memory(GiB)": 26.92, "elapsed_time": "1h 55m 56s", "remaining_time": "1h 37m 52s", "loss_scale": 1.0, "consumed_samples": 8320, "global_step/max_steps": "520/959"} +{"lm loss": 0.63521461, "load_balancing_loss": 1.2023385, "grad_norm": 2.01469064, "learning_rate": 5.17e-06, "elapsed_time_per_iteration": 12.71734023, "memory(GiB)": 26.92, "elapsed_time": "1h 56m 59s", "remaining_time": "1h 36m 43s", "loss_scale": 1.0, "consumed_samples": 8400, "global_step/max_steps": "525/959"} +{"lm loss": 0.6640408, "load_balancing_loss": 1.22768793, "grad_norm": 1.94587505, "learning_rate": 5.09e-06, "elapsed_time_per_iteration": 13.09642253, "memory(GiB)": 26.92, "elapsed_time": "1h 58m 5s", "remaining_time": "1h 35m 35s", "loss_scale": 1.0, "consumed_samples": 8480, "global_step/max_steps": "530/959"} +{"lm loss": 0.67727523, "load_balancing_loss": 1.23195858, "grad_norm": 1.5471555, "learning_rate": 5.01e-06, "elapsed_time_per_iteration": 13.32476516, "memory(GiB)": 26.92, "elapsed_time": "1h 59m 11s", "remaining_time": "1h 34m 28s", "loss_scale": 1.0, "consumed_samples": 8560, "global_step/max_steps": "535/959"} +{"lm loss": 0.67374911, "load_balancing_loss": 1.21887722, "grad_norm": 2.2618072, "learning_rate": 4.93e-06, "elapsed_time_per_iteration": 13.13169684, "memory(GiB)": 30.08, "elapsed_time": "2h 0m 17s", "remaining_time": "1h 33m 20s", "loss_scale": 1.0, "consumed_samples": 8640, "global_step/max_steps": "540/959"} +{"lm loss": 0.68080873, "load_balancing_loss": 1.21103706, "grad_norm": 1.82543111, "learning_rate": 4.86e-06, "elapsed_time_per_iteration": 13.05666871, "memory(GiB)": 30.08, "elapsed_time": "2h 1m 22s", "remaining_time": "1h 32m 12s", "loss_scale": 1.0, "consumed_samples": 8720, "global_step/max_steps": "545/959"} +{"lm loss": 0.66799397, "load_balancing_loss": 1.23056107, "grad_norm": 2.00670815, "learning_rate": 4.78e-06, "elapsed_time_per_iteration": 13.22996545, "memory(GiB)": 30.08, "elapsed_time": "2h 2m 29s", "remaining_time": "1h 31m 5s", "loss_scale": 1.0, "consumed_samples": 8800, "global_step/max_steps": "550/959"} +{"lm loss": 0.66009483, "load_balancing_loss": 1.20875893, "grad_norm": 1.73200285, "learning_rate": 4.7e-06, "elapsed_time_per_iteration": 13.49006381, "memory(GiB)": 30.08, "elapsed_time": "2h 3m 36s", "remaining_time": "1h 29m 58s", "loss_scale": 1.0, "consumed_samples": 8880, "global_step/max_steps": "555/959"} +{"lm loss": 0.65673552, "load_balancing_loss": 1.1957922, "grad_norm": 1.40053463, "learning_rate": 4.63e-06, "elapsed_time_per_iteration": 13.23073878, "memory(GiB)": 30.08, "elapsed_time": "2h 4m 42s", "remaining_time": "1h 28m 51s", "loss_scale": 1.0, "consumed_samples": 8960, "global_step/max_steps": "560/959"} +{"lm loss": 0.66083326, "load_balancing_loss": 1.22290716, "grad_norm": 2.54822445, "learning_rate": 4.55e-06, "elapsed_time_per_iteration": 13.23673353, "memory(GiB)": 30.08, "elapsed_time": "2h 5m 48s", "remaining_time": "1h 27m 44s", "loss_scale": 1.0, "consumed_samples": 9040, "global_step/max_steps": "565/959"} +{"lm loss": 0.65971627, "load_balancing_loss": 1.20782585, "grad_norm": 1.70622706, "learning_rate": 4.48e-06, "elapsed_time_per_iteration": 13.49629016, "memory(GiB)": 30.08, "elapsed_time": "2h 6m 56s", "remaining_time": "1h 26m 37s", "loss_scale": 1.0, "consumed_samples": 9120, "global_step/max_steps": "570/959"} +{"lm loss": 0.67082095, "load_balancing_loss": 1.21638517, "grad_norm": 3.55180287, "learning_rate": 4.4e-06, "elapsed_time_per_iteration": 13.21600513, "memory(GiB)": 30.08, "elapsed_time": "2h 8m 2s", "remaining_time": "1h 25m 30s", "loss_scale": 1.0, "consumed_samples": 9200, "global_step/max_steps": "575/959"} +{"lm loss": 0.63578758, "load_balancing_loss": 1.19922094, "grad_norm": 2.50419998, "learning_rate": 4.33e-06, "elapsed_time_per_iteration": 13.76897869, "memory(GiB)": 30.08, "elapsed_time": "2h 9m 11s", "remaining_time": "1h 24m 25s", "loss_scale": 1.0, "consumed_samples": 9280, "global_step/max_steps": "580/959"} +{"lm loss": 0.6733902, "load_balancing_loss": 1.20800591, "grad_norm": 2.32680392, "learning_rate": 4.25e-06, "elapsed_time_per_iteration": 13.84015932, "memory(GiB)": 30.08, "elapsed_time": "2h 10m 20s", "remaining_time": "1h 23m 19s", "loss_scale": 1.0, "consumed_samples": 9360, "global_step/max_steps": "585/959"} +{"lm loss": 0.67681732, "load_balancing_loss": 1.23406086, "grad_norm": 2.18602276, "learning_rate": 4.18e-06, "elapsed_time_per_iteration": 12.80892453, "memory(GiB)": 30.08, "elapsed_time": "2h 11m 24s", "remaining_time": "1h 22m 11s", "loss_scale": 1.0, "consumed_samples": 9440, "global_step/max_steps": "590/959"} +{"lm loss": 0.6572381, "load_balancing_loss": 1.19761801, "grad_norm": 1.90373015, "learning_rate": 4.1e-06, "elapsed_time_per_iteration": 13.31592798, "memory(GiB)": 30.08, "elapsed_time": "2h 12m 31s", "remaining_time": "1h 21m 4s", "loss_scale": 1.0, "consumed_samples": 9520, "global_step/max_steps": "595/959"} +{"lm loss": 0.6710578, "load_balancing_loss": 1.18883648, "grad_norm": 2.18903494, "learning_rate": 4.03e-06, "elapsed_time_per_iteration": 13.80694814, "memory(GiB)": 30.08, "elapsed_time": "2h 13m 40s", "remaining_time": "1h 19m 58s", "loss_scale": 1.0, "consumed_samples": 9600, "global_step/max_steps": "600/959"} +{"lm loss": 0.66662788, "load_balancing_loss": 1.22197304, "grad_norm": 8.43059349, "learning_rate": 3.96e-06, "elapsed_time_per_iteration": 13.05821333, "memory(GiB)": 30.08, "elapsed_time": "2h 14m 45s", "remaining_time": "1h 18m 50s", "loss_scale": 1.0, "consumed_samples": 9680, "global_step/max_steps": "605/959"} +{"lm loss": 0.6678421, "load_balancing_loss": 1.20340576, "grad_norm": 1.81959414, "learning_rate": 3.88e-06, "elapsed_time_per_iteration": 13.32898197, "memory(GiB)": 30.08, "elapsed_time": "2h 15m 52s", "remaining_time": "1h 17m 44s", "loss_scale": 1.0, "consumed_samples": 9760, "global_step/max_steps": "610/959"} +{"lm loss": 0.64665594, "load_balancing_loss": 1.19327736, "grad_norm": 1.83581376, "learning_rate": 3.81e-06, "elapsed_time_per_iteration": 13.65110354, "memory(GiB)": 30.08, "elapsed_time": "2h 17m 0s", "remaining_time": "1h 16m 38s", "loss_scale": 1.0, "consumed_samples": 9840, "global_step/max_steps": "615/959"} +{"lm loss": 0.68168297, "load_balancing_loss": 1.23152924, "grad_norm": 2.62215686, "learning_rate": 3.74e-06, "elapsed_time_per_iteration": 13.39657764, "memory(GiB)": 30.08, "elapsed_time": "2h 18m 7s", "remaining_time": "1h 15m 31s", "loss_scale": 1.0, "consumed_samples": 9920, "global_step/max_steps": "620/959"} +{"lm loss": 0.64839973, "load_balancing_loss": 1.21048346, "grad_norm": 2.20388865, "learning_rate": 3.67e-06, "elapsed_time_per_iteration": 13.1182447, "memory(GiB)": 30.08, "elapsed_time": "2h 19m 12s", "remaining_time": "1h 14m 23s", "loss_scale": 1.0, "consumed_samples": 10000, "global_step/max_steps": "625/959"} +{"lm loss": 0.67100167, "load_balancing_loss": 1.20946131, "grad_norm": 2.1443224, "learning_rate": 3.6e-06, "elapsed_time_per_iteration": 13.38485141, "memory(GiB)": 30.08, "elapsed_time": "2h 20m 19s", "remaining_time": "1h 13m 17s", "loss_scale": 1.0, "consumed_samples": 10080, "global_step/max_steps": "630/959"} +{"lm loss": 0.63081698, "load_balancing_loss": 1.22941084, "grad_norm": 2.44609547, "learning_rate": 3.53e-06, "elapsed_time_per_iteration": 13.1453505, "memory(GiB)": 30.08, "elapsed_time": "2h 21m 25s", "remaining_time": "1h 12m 9s", "loss_scale": 1.0, "consumed_samples": 10160, "global_step/max_steps": "635/959"} +{"lm loss": 0.63907628, "load_balancing_loss": 1.21154928, "grad_norm": 1.99117565, "learning_rate": 3.46e-06, "elapsed_time_per_iteration": 13.01295962, "memory(GiB)": 30.08, "elapsed_time": "2h 22m 30s", "remaining_time": "1h 11m 1s", "loss_scale": 1.0, "consumed_samples": 10240, "global_step/max_steps": "640/959"} +{"lm loss": 0.68653231, "load_balancing_loss": 1.20454865, "grad_norm": 1.81538808, "learning_rate": 3.39e-06, "elapsed_time_per_iteration": 13.38480935, "memory(GiB)": 30.08, "elapsed_time": "2h 23m 37s", "remaining_time": "1h 9m 55s", "loss_scale": 1.0, "consumed_samples": 10320, "global_step/max_steps": "645/959"} +{"lm loss": 0.6677207, "load_balancing_loss": 1.20553179, "grad_norm": 2.43817878, "learning_rate": 3.32e-06, "elapsed_time_per_iteration": 13.75242829, "memory(GiB)": 30.08, "elapsed_time": "2h 24m 46s", "remaining_time": "1h 8m 49s", "loss_scale": 1.0, "consumed_samples": 10400, "global_step/max_steps": "650/959"} +{"lm loss": 0.65095363, "load_balancing_loss": 1.21655016, "grad_norm": 1.86884022, "learning_rate": 3.25e-06, "elapsed_time_per_iteration": 13.22745643, "memory(GiB)": 30.08, "elapsed_time": "2h 25m 52s", "remaining_time": "1h 7m 42s", "loss_scale": 1.0, "consumed_samples": 10480, "global_step/max_steps": "655/959"} +{"lm loss": 0.66017122, "load_balancing_loss": 1.21038828, "grad_norm": 1.7580601, "learning_rate": 3.19e-06, "elapsed_time_per_iteration": 13.15733457, "memory(GiB)": 30.08, "elapsed_time": "2h 26m 58s", "remaining_time": "1h 6m 34s", "loss_scale": 1.0, "consumed_samples": 10560, "global_step/max_steps": "660/959"} +{"lm loss": 0.64331422, "load_balancing_loss": 1.2033186, "grad_norm": 2.77984977, "learning_rate": 3.12e-06, "elapsed_time_per_iteration": 13.41416593, "memory(GiB)": 30.08, "elapsed_time": "2h 28m 5s", "remaining_time": "1h 5m 28s", "loss_scale": 1.0, "consumed_samples": 10640, "global_step/max_steps": "665/959"} +{"lm loss": 0.66049042, "load_balancing_loss": 1.2079484, "grad_norm": 1.62225819, "learning_rate": 3.06e-06, "elapsed_time_per_iteration": 13.35066166, "memory(GiB)": 30.08, "elapsed_time": "2h 29m 12s", "remaining_time": "1h 4m 21s", "loss_scale": 1.0, "consumed_samples": 10720, "global_step/max_steps": "670/959"} +{"lm loss": 0.63504944, "load_balancing_loss": 1.20621758, "grad_norm": 2.64649034, "learning_rate": 2.99e-06, "elapsed_time_per_iteration": 12.94294071, "memory(GiB)": 30.08, "elapsed_time": "2h 30m 16s", "remaining_time": "1h 3m 13s", "loss_scale": 1.0, "consumed_samples": 10800, "global_step/max_steps": "675/959"} +{"lm loss": 0.6493444, "load_balancing_loss": 1.21133795, "grad_norm": 2.43453002, "learning_rate": 2.93e-06, "elapsed_time_per_iteration": 13.24355512, "memory(GiB)": 30.08, "elapsed_time": "2h 31m 22s", "remaining_time": "1h 2m 6s", "loss_scale": 1.0, "consumed_samples": 10880, "global_step/max_steps": "680/959"} +{"lm loss": 0.66395483, "load_balancing_loss": 1.21860237, "grad_norm": 1.97231114, "learning_rate": 2.86e-06, "elapsed_time_per_iteration": 13.64731054, "memory(GiB)": 30.08, "elapsed_time": "2h 32m 31s", "remaining_time": "1h 1m 0s", "loss_scale": 1.0, "consumed_samples": 10960, "global_step/max_steps": "685/959"} +{"lm loss": 0.65285606, "load_balancing_loss": 1.20617943, "grad_norm": 1.99314439, "learning_rate": 2.8e-06, "elapsed_time_per_iteration": 12.9457727, "memory(GiB)": 30.08, "elapsed_time": "2h 33m 35s", "remaining_time": "59m 52s", "loss_scale": 1.0, "consumed_samples": 11040, "global_step/max_steps": "690/959"} +{"lm loss": 0.68385868, "load_balancing_loss": 1.2070549, "grad_norm": 1.50443935, "learning_rate": 2.74e-06, "elapsed_time_per_iteration": 13.03916759, "memory(GiB)": 30.08, "elapsed_time": "2h 34m 41s", "remaining_time": "58m 45s", "loss_scale": 1.0, "consumed_samples": 11120, "global_step/max_steps": "695/959"} +{"lm loss": 0.66196518, "load_balancing_loss": 1.21173048, "grad_norm": 1.73470533, "learning_rate": 2.68e-06, "elapsed_time_per_iteration": 13.17870789, "memory(GiB)": 30.08, "elapsed_time": "2h 35m 47s", "remaining_time": "57m 38s", "loss_scale": 1.0, "consumed_samples": 11200, "global_step/max_steps": "700/959"} +{"lm loss": 0.66838279, "load_balancing_loss": 1.21968069, "grad_norm": 1.68811953, "learning_rate": 2.62e-06, "elapsed_time_per_iteration": 13.26609097, "memory(GiB)": 30.08, "elapsed_time": "2h 36m 53s", "remaining_time": "56m 31s", "loss_scale": 1.0, "consumed_samples": 11280, "global_step/max_steps": "705/959"} +{"lm loss": 0.64856844, "load_balancing_loss": 1.2125144, "grad_norm": 1.97252774, "learning_rate": 2.56e-06, "elapsed_time_per_iteration": 12.89892826, "memory(GiB)": 30.08, "elapsed_time": "2h 37m 57s", "remaining_time": "55m 23s", "loss_scale": 1.0, "consumed_samples": 11360, "global_step/max_steps": "710/959"} +{"lm loss": 0.65430703, "load_balancing_loss": 1.21629181, "grad_norm": 2.1413157, "learning_rate": 2.5e-06, "elapsed_time_per_iteration": 13.33657041, "memory(GiB)": 30.08, "elapsed_time": "2h 39m 4s", "remaining_time": "54m 17s", "loss_scale": 1.0, "consumed_samples": 11440, "global_step/max_steps": "715/959"} +{"lm loss": 0.66335058, "load_balancing_loss": 1.24045048, "grad_norm": 1.78750122, "learning_rate": 2.44e-06, "elapsed_time_per_iteration": 13.48199859, "memory(GiB)": 30.08, "elapsed_time": "2h 40m 11s", "remaining_time": "53m 10s", "loss_scale": 1.0, "consumed_samples": 11520, "global_step/max_steps": "720/959"} +{"lm loss": 0.65938997, "load_balancing_loss": 1.20611458, "grad_norm": 2.3621161, "learning_rate": 2.39e-06, "elapsed_time_per_iteration": 13.09419761, "memory(GiB)": 30.08, "elapsed_time": "2h 41m 17s", "remaining_time": "52m 3s", "loss_scale": 1.0, "consumed_samples": 11600, "global_step/max_steps": "725/959"} +{"lm loss": 0.6561265, "load_balancing_loss": 1.20162983, "grad_norm": 2.91820574, "learning_rate": 2.33e-06, "elapsed_time_per_iteration": 13.45152283, "memory(GiB)": 30.08, "elapsed_time": "2h 42m 24s", "remaining_time": "50m 56s", "loss_scale": 1.0, "consumed_samples": 11680, "global_step/max_steps": "730/959"} +{"lm loss": 0.64716334, "load_balancing_loss": 1.19702606, "grad_norm": 2.55184317, "learning_rate": 2.28e-06, "elapsed_time_per_iteration": 13.50867972, "memory(GiB)": 30.08, "elapsed_time": "2h 43m 32s", "remaining_time": "49m 50s", "loss_scale": 1.0, "consumed_samples": 11760, "global_step/max_steps": "735/959"} +{"lm loss": 0.69388428, "load_balancing_loss": 1.23029957, "grad_norm": 1.87346399, "learning_rate": 2.22e-06, "elapsed_time_per_iteration": 12.87756801, "memory(GiB)": 30.08, "elapsed_time": "2h 44m 36s", "remaining_time": "48m 42s", "loss_scale": 1.0, "consumed_samples": 11840, "global_step/max_steps": "740/959"} +{"lm loss": 0.65987635, "load_balancing_loss": 1.22693024, "grad_norm": 1.69717503, "learning_rate": 2.17e-06, "elapsed_time_per_iteration": 13.16368833, "memory(GiB)": 30.08, "elapsed_time": "2h 45m 42s", "remaining_time": "47m 35s", "loss_scale": 1.0, "consumed_samples": 11920, "global_step/max_steps": "745/959"} +{"lm loss": 0.65470495, "load_balancing_loss": 1.20077333, "grad_norm": 2.21245503, "learning_rate": 2.12e-06, "elapsed_time_per_iteration": 13.84619284, "memory(GiB)": 30.08, "elapsed_time": "2h 46m 51s", "remaining_time": "46m 29s", "loss_scale": 1.0, "consumed_samples": 12000, "global_step/max_steps": "750/959"} +{"lm loss": 0.69013643, "load_balancing_loss": 1.19529104, "grad_norm": 2.45334649, "learning_rate": 2.07e-06, "elapsed_time_per_iteration": 13.32114444, "memory(GiB)": 30.08, "elapsed_time": "2h 47m 58s", "remaining_time": "45m 23s", "loss_scale": 1.0, "consumed_samples": 12080, "global_step/max_steps": "755/959"} +{"lm loss": 0.64197292, "load_balancing_loss": 1.21952038, "grad_norm": 2.14006901, "learning_rate": 2.02e-06, "elapsed_time_per_iteration": 12.78434601, "memory(GiB)": 30.08, "elapsed_time": "2h 49m 2s", "remaining_time": "44m 15s", "loss_scale": 1.0, "consumed_samples": 12160, "global_step/max_steps": "760/959"} +{"lm loss": 0.66176906, "load_balancing_loss": 1.23241329, "grad_norm": 1.81270504, "learning_rate": 1.97e-06, "elapsed_time_per_iteration": 13.28880153, "memory(GiB)": 30.08, "elapsed_time": "2h 50m 8s", "remaining_time": "43m 8s", "loss_scale": 1.0, "consumed_samples": 12240, "global_step/max_steps": "765/959"} +{"lm loss": 0.67052884, "load_balancing_loss": 1.2024745, "grad_norm": 2.15456486, "learning_rate": 1.92e-06, "elapsed_time_per_iteration": 13.27301793, "memory(GiB)": 30.08, "elapsed_time": "2h 51m 15s", "remaining_time": "42m 2s", "loss_scale": 1.0, "consumed_samples": 12320, "global_step/max_steps": "770/959"} +{"lm loss": 0.65434041, "load_balancing_loss": 1.24514027, "grad_norm": 2.75546551, "learning_rate": 1.88e-06, "elapsed_time_per_iteration": 12.99600019, "memory(GiB)": 30.08, "elapsed_time": "2h 52m 19s", "remaining_time": "40m 54s", "loss_scale": 1.0, "consumed_samples": 12400, "global_step/max_steps": "775/959"} +{"lm loss": 0.65868893, "load_balancing_loss": 1.22991199, "grad_norm": 1.56302655, "learning_rate": 1.83e-06, "elapsed_time_per_iteration": 13.19650149, "memory(GiB)": 30.08, "elapsed_time": "2h 53m 25s", "remaining_time": "39m 48s", "loss_scale": 1.0, "consumed_samples": 12480, "global_step/max_steps": "780/959"} +{"lm loss": 0.64579673, "load_balancing_loss": 1.19464407, "grad_norm": 2.35680079, "learning_rate": 1.79e-06, "elapsed_time_per_iteration": 13.78021078, "memory(GiB)": 30.08, "elapsed_time": "2h 54m 34s", "remaining_time": "38m 41s", "loss_scale": 1.0, "consumed_samples": 12560, "global_step/max_steps": "785/959"} +{"lm loss": 0.64300814, "load_balancing_loss": 1.20580063, "grad_norm": 3.77633381, "learning_rate": 1.74e-06, "elapsed_time_per_iteration": 13.11096029, "memory(GiB)": 30.08, "elapsed_time": "2h 55m 40s", "remaining_time": "37m 34s", "loss_scale": 1.0, "consumed_samples": 12640, "global_step/max_steps": "790/959"} +{"lm loss": 0.64244676, "load_balancing_loss": 1.23189135, "grad_norm": 2.09976721, "learning_rate": 1.7e-06, "elapsed_time_per_iteration": 13.22479177, "memory(GiB)": 30.08, "elapsed_time": "2h 56m 46s", "remaining_time": "36m 28s", "loss_scale": 1.0, "consumed_samples": 12720, "global_step/max_steps": "795/959"} +{"lm loss": 0.64825253, "load_balancing_loss": 1.19707251, "grad_norm": 4.25277662, "learning_rate": 1.66e-06, "elapsed_time_per_iteration": 13.69236908, "memory(GiB)": 30.08, "elapsed_time": "2h 57m 55s", "remaining_time": "35m 21s", "loss_scale": 1.0, "consumed_samples": 12800, "global_step/max_steps": "800/959"} +{"lm loss": 0.64379897, "load_balancing_loss": 1.21160326, "grad_norm": 2.49628162, "learning_rate": 1.62e-06, "elapsed_time_per_iteration": 13.01428404, "memory(GiB)": 30.08, "elapsed_time": "2h 59m 0s", "remaining_time": "34m 14s", "loss_scale": 1.0, "consumed_samples": 12880, "global_step/max_steps": "805/959"} +{"lm loss": 0.66808147, "load_balancing_loss": 1.22591286, "grad_norm": 1.91681671, "learning_rate": 1.58e-06, "elapsed_time_per_iteration": 13.08678379, "memory(GiB)": 30.08, "elapsed_time": "3h 0m 5s", "remaining_time": "33m 7s", "loss_scale": 1.0, "consumed_samples": 12960, "global_step/max_steps": "810/959"} +{"lm loss": 0.6620399, "load_balancing_loss": 1.21884327, "grad_norm": 2.12716317, "learning_rate": 1.54e-06, "elapsed_time_per_iteration": 13.17482238, "memory(GiB)": 30.08, "elapsed_time": "3h 1m 11s", "remaining_time": "32m 0s", "loss_scale": 1.0, "consumed_samples": 13040, "global_step/max_steps": "815/959"} +{"lm loss": 0.63634458, "load_balancing_loss": 1.19833889, "grad_norm": 1.88539517, "learning_rate": 1.51e-06, "elapsed_time_per_iteration": 13.47562246, "memory(GiB)": 30.08, "elapsed_time": "3h 2m 18s", "remaining_time": "30m 54s", "loss_scale": 1.0, "consumed_samples": 13120, "global_step/max_steps": "820/959"} +{"lm loss": 0.65701952, "load_balancing_loss": 1.22195778, "grad_norm": 2.00650573, "learning_rate": 1.47e-06, "elapsed_time_per_iteration": 13.11556993, "memory(GiB)": 30.08, "elapsed_time": "3h 3m 24s", "remaining_time": "29m 47s", "loss_scale": 1.0, "consumed_samples": 13200, "global_step/max_steps": "825/959"} +{"lm loss": 0.64520302, "load_balancing_loss": 1.20261211, "grad_norm": 1.89828753, "learning_rate": 1.44e-06, "elapsed_time_per_iteration": 13.6522449, "memory(GiB)": 30.08, "elapsed_time": "3h 4m 32s", "remaining_time": "28m 40s", "loss_scale": 1.0, "consumed_samples": 13280, "global_step/max_steps": "830/959"} +{"lm loss": 0.65779638, "load_balancing_loss": 1.21705532, "grad_norm": 3.21512175, "learning_rate": 1.41e-06, "elapsed_time_per_iteration": 13.27440443, "memory(GiB)": 30.08, "elapsed_time": "3h 5m 38s", "remaining_time": "27m 34s", "loss_scale": 1.0, "consumed_samples": 13360, "global_step/max_steps": "835/959"} +{"lm loss": 0.68138523, "load_balancing_loss": 1.20344162, "grad_norm": 1.87987947, "learning_rate": 1.37e-06, "elapsed_time_per_iteration": 13.00519872, "memory(GiB)": 30.08, "elapsed_time": "3h 6m 44s", "remaining_time": "26m 27s", "loss_scale": 1.0, "consumed_samples": 13440, "global_step/max_steps": "840/959"} +{"lm loss": 0.65426073, "load_balancing_loss": 1.20452518, "grad_norm": 2.189605, "learning_rate": 1.34e-06, "elapsed_time_per_iteration": 13.276794, "memory(GiB)": 30.08, "elapsed_time": "3h 7m 50s", "remaining_time": "25m 20s", "loss_scale": 1.0, "consumed_samples": 13520, "global_step/max_steps": "845/959"} +{"lm loss": 0.60918298, "load_balancing_loss": 1.21420822, "grad_norm": 2.72332287, "learning_rate": 1.31e-06, "elapsed_time_per_iteration": 13.32150145, "memory(GiB)": 30.08, "elapsed_time": "3h 8m 56s", "remaining_time": "24m 13s", "loss_scale": 1.0, "consumed_samples": 13600, "global_step/max_steps": "850/959"} +{"lm loss": 0.65472536, "load_balancing_loss": 1.19700661, "grad_norm": 2.16305757, "learning_rate": 1.29e-06, "elapsed_time_per_iteration": 13.53804212, "memory(GiB)": 30.08, "elapsed_time": "3h 10m 4s", "remaining_time": "23m 7s", "loss_scale": 1.0, "consumed_samples": 13680, "global_step/max_steps": "855/959"} +{"lm loss": 0.62973199, "load_balancing_loss": 1.20247498, "grad_norm": 2.90722561, "learning_rate": 1.26e-06, "elapsed_time_per_iteration": 13.27226534, "memory(GiB)": 30.08, "elapsed_time": "3h 11m 11s", "remaining_time": "22m 0s", "loss_scale": 1.0, "consumed_samples": 13760, "global_step/max_steps": "860/959"} +{"lm loss": 0.63398042, "load_balancing_loss": 1.20888834, "grad_norm": 1.62707722, "learning_rate": 1.23e-06, "elapsed_time_per_iteration": 12.99460664, "memory(GiB)": 30.08, "elapsed_time": "3h 12m 16s", "remaining_time": "20m 53s", "loss_scale": 1.0, "consumed_samples": 13840, "global_step/max_steps": "865/959"} +{"lm loss": 0.65810347, "load_balancing_loss": 1.21169052, "grad_norm": 2.1192584, "learning_rate": 1.21e-06, "elapsed_time_per_iteration": 13.46534462, "memory(GiB)": 30.08, "elapsed_time": "3h 13m 23s", "remaining_time": "19m 47s", "loss_scale": 1.0, "consumed_samples": 13920, "global_step/max_steps": "870/959"} +{"lm loss": 0.66496134, "load_balancing_loss": 1.2129097, "grad_norm": 2.69365788, "learning_rate": 1.19e-06, "elapsed_time_per_iteration": 13.13649793, "memory(GiB)": 30.08, "elapsed_time": "3h 14m 29s", "remaining_time": "18m 40s", "loss_scale": 1.0, "consumed_samples": 14000, "global_step/max_steps": "875/959"} +{"lm loss": 0.6507277, "load_balancing_loss": 1.2236968, "grad_norm": 2.27486873, "learning_rate": 1.17e-06, "elapsed_time_per_iteration": 13.10092468, "memory(GiB)": 30.08, "elapsed_time": "3h 15m 34s", "remaining_time": "17m 33s", "loss_scale": 1.0, "consumed_samples": 14080, "global_step/max_steps": "880/959"} +{"lm loss": 0.63180122, "load_balancing_loss": 1.19793472, "grad_norm": 1.65658879, "learning_rate": 1.15e-06, "elapsed_time_per_iteration": 13.69119473, "memory(GiB)": 30.08, "elapsed_time": "3h 16m 42s", "remaining_time": "16m 26s", "loss_scale": 1.0, "consumed_samples": 14160, "global_step/max_steps": "885/959"} +{"lm loss": 0.63257723, "load_balancing_loss": 1.20171909, "grad_norm": 2.38219666, "learning_rate": 1.13e-06, "elapsed_time_per_iteration": 13.24639506, "memory(GiB)": 30.08, "elapsed_time": "3h 17m 49s", "remaining_time": "15m 20s", "loss_scale": 1.0, "consumed_samples": 14240, "global_step/max_steps": "890/959"} +{"lm loss": 0.65380325, "load_balancing_loss": 1.21711636, "grad_norm": 2.33846474, "learning_rate": 1.11e-06, "elapsed_time_per_iteration": 13.02140541, "memory(GiB)": 30.08, "elapsed_time": "3h 18m 54s", "remaining_time": "14m 13s", "loss_scale": 1.0, "consumed_samples": 14320, "global_step/max_steps": "895/959"} +{"lm loss": 0.66698542, "load_balancing_loss": 1.2158474, "grad_norm": 1.26327932, "learning_rate": 1.09e-06, "elapsed_time_per_iteration": 12.69746614, "memory(GiB)": 30.08, "elapsed_time": "3h 19m 57s", "remaining_time": "13m 6s", "loss_scale": 1.0, "consumed_samples": 14400, "global_step/max_steps": "900/959"} +{"lm loss": 0.63434873, "load_balancing_loss": 1.1963026, "grad_norm": 2.51440859, "learning_rate": 1.08e-06, "elapsed_time_per_iteration": 13.74776268, "memory(GiB)": 33.39, "elapsed_time": "3h 21m 6s", "remaining_time": "11m 59s", "loss_scale": 1.0, "consumed_samples": 14480, "global_step/max_steps": "905/959"} +{"lm loss": 0.6531136, "load_balancing_loss": 1.21672478, "grad_norm": 2.97008777, "learning_rate": 1.06e-06, "elapsed_time_per_iteration": 13.14819851, "memory(GiB)": 33.39, "elapsed_time": "3h 22m 12s", "remaining_time": "10m 53s", "loss_scale": 1.0, "consumed_samples": 14560, "global_step/max_steps": "910/959"} +{"lm loss": 0.66523223, "load_balancing_loss": 1.20480318, "grad_norm": 1.88266778, "learning_rate": 1.05e-06, "elapsed_time_per_iteration": 13.26519299, "memory(GiB)": 33.39, "elapsed_time": "3h 23m 18s", "remaining_time": "9m 46s", "loss_scale": 1.0, "consumed_samples": 14640, "global_step/max_steps": "915/959"} +{"lm loss": 0.67144995, "load_balancing_loss": 1.24200115, "grad_norm": 1.86340261, "learning_rate": 1.04e-06, "elapsed_time_per_iteration": 12.99693122, "memory(GiB)": 33.39, "elapsed_time": "3h 24m 23s", "remaining_time": "8m 39s", "loss_scale": 1.0, "consumed_samples": 14720, "global_step/max_steps": "920/959"} +{"lm loss": 0.64737287, "load_balancing_loss": 1.24051914, "grad_norm": 1.94958258, "learning_rate": 1.03e-06, "elapsed_time_per_iteration": 12.61661282, "memory(GiB)": 33.39, "elapsed_time": "3h 25m 26s", "remaining_time": "7m 33s", "loss_scale": 1.0, "consumed_samples": 14800, "global_step/max_steps": "925/959"} +{"lm loss": 0.64937649, "load_balancing_loss": 1.21176968, "grad_norm": 1.7903235, "learning_rate": 1.02e-06, "elapsed_time_per_iteration": 13.19775648, "memory(GiB)": 33.39, "elapsed_time": "3h 26m 32s", "remaining_time": "6m 26s", "loss_scale": 1.0, "consumed_samples": 14880, "global_step/max_steps": "930/959"} +{"lm loss": 0.64613228, "load_balancing_loss": 1.20786629, "grad_norm": 1.77396524, "learning_rate": 1.02e-06, "elapsed_time_per_iteration": 13.42089596, "memory(GiB)": 33.39, "elapsed_time": "3h 27m 39s", "remaining_time": "5m 19s", "loss_scale": 1.0, "consumed_samples": 14960, "global_step/max_steps": "935/959"} +{"lm loss": 0.65868797, "load_balancing_loss": 1.21492233, "grad_norm": 2.13642383, "learning_rate": 1.01e-06, "elapsed_time_per_iteration": 12.89135652, "memory(GiB)": 33.39, "elapsed_time": "3h 28m 44s", "remaining_time": "4m 13s", "loss_scale": 1.0, "consumed_samples": 15040, "global_step/max_steps": "940/959"} +{"lm loss": 0.6487, "load_balancing_loss": 1.20925856, "grad_norm": 1.8813256, "learning_rate": 1.01e-06, "elapsed_time_per_iteration": 13.32083898, "memory(GiB)": 33.39, "elapsed_time": "3h 29m 50s", "remaining_time": "3m 6s", "loss_scale": 1.0, "consumed_samples": 15120, "global_step/max_steps": "945/959"} +{"lm loss": 0.64507337, "load_balancing_loss": 1.19633026, "grad_norm": 3.02795792, "learning_rate": 1e-06, "elapsed_time_per_iteration": 13.4453855, "memory(GiB)": 33.39, "elapsed_time": "3h 30m 58s", "remaining_time": "1m 59s", "loss_scale": 1.0, "consumed_samples": 15200, "global_step/max_steps": "950/959"} +{"lm loss": 0.66384897, "load_balancing_loss": 1.20863609, "grad_norm": 1.67091453, "learning_rate": 1e-06, "elapsed_time_per_iteration": 13.3173975, "memory(GiB)": 33.39, "elapsed_time": "3h 32m 4s", "remaining_time": "53s", "loss_scale": 1.0, "consumed_samples": 15280, "global_step/max_steps": "955/959"} diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/runs/events.out.tfevents.1770955123.n124-174-111.2055620.0 b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/runs/events.out.tfevents.1770955123.n124-174-111.2055620.0 new file mode 100644 index 0000000000000000000000000000000000000000..d7077871119d9b0541d7ff58b510f437fb834db9 --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/runs/events.out.tfevents.1770955123.n124-174-111.2055620.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2c6e2b05789499d4d402455775efb9a42d7a09656789433f84fcf9ebcd1357c +size 733135 diff --git a/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/runs/events.out.tfevents.1770969015.n124-174-111.2160846.0 b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/runs/events.out.tfevents.1770969015.n124-174-111.2160846.0 new file mode 100644 index 0000000000000000000000000000000000000000..eaaca2bf8b72dd1cd399e65b4438da08f39c2f8e --- /dev/null +++ b/posttrain_models/qwen3vl_30b_highlight_batch1_epoch4_lora/runs/events.out.tfevents.1770969015.n124-174-111.2160846.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:138ed470b3f6c76e44a67af48bcd9cdab12f288c5bbcfeef9acfe1ed702e2c8d +size 883798 diff --git a/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765277604.n124-174-123.3970260.0 b/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765277604.n124-174-123.3970260.0 new file mode 100644 index 0000000000000000000000000000000000000000..18692fe91146642b30aa9ef83e39583963b0a546 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765277604.n124-174-123.3970260.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c15598e42f1d1d533f2c5ebcb844a848e96123d77e5d58b0db87c5b3e3125ab +size 6691 diff --git a/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765278719.n124-174-123.793782.0 b/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765278719.n124-174-123.793782.0 new file mode 100644 index 0000000000000000000000000000000000000000..8594a0288ce6ba760026008c25c4f239d213b407 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765278719.n124-174-123.793782.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea5f8921ba32e8b7e050184930d3c202bb53065f3c08aef3eb52c25d1c49bf96 +size 6691 diff --git a/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765279192.n124-174-123.854426.0 b/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765279192.n124-174-123.854426.0 new file mode 100644 index 0000000000000000000000000000000000000000..fb0bbba5e111d25db159ab1d4720a637a15b98c0 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765279192.n124-174-123.854426.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c946ff4757ed5b1a12a2ce584e6697f5ba9c02540dd84f8ce045b0938895e660 +size 6691 diff --git a/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765279311.n124-174-123.899687.0 b/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765279311.n124-174-123.899687.0 new file mode 100644 index 0000000000000000000000000000000000000000..acaf032c774c0ecb92cbe0cf44029abe2110bdc3 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765279311.n124-174-123.899687.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6200a343bcb0af88037f46f1c302770ab0124237049b5fc65a988dfd60c60b7f +size 6691 diff --git a/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765279532.n124-174-123.945118.0 b/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765279532.n124-174-123.945118.0 new file mode 100644 index 0000000000000000000000000000000000000000..81c8fda14b9b8b078f1e96f8c8b8faac464ab9ef --- /dev/null +++ b/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/runs/logging/events.out.tfevents.1765279532.n124-174-123.945118.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78bcaea6f0bf88f1a70b44c6de848f150291ef1d36ba432029cb3482cf3dc362 +size 6691 diff --git a/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/training_config.yaml b/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/training_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..63b6c1dee623555c561c43d6b1bc8091ca01037d --- /dev/null +++ b/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/training_config.yaml @@ -0,0 +1,77 @@ +DATA_CONFIG: + datasources: + OSSDATA: + - data_file: /opt/tiger/tanyue/highlight_sft_smallvlm/data/charades-sta/train_w_cot_aligned.json + data_type: llava_video + dataset_type: qwen3vl_video + image_dir: /mnt/bn/strategy-mllm-train/common/temporal_grounding_data/ + - data_file: /opt/tiger/tanyue/highlight_sft_smallvlm/data/activitynet/train_w_cot_aligned.json + data_type: llava_video + dataset_type: qwen3vl_video + image_dir: /mnt/bn/strategy-mllm-train/common/temporal_grounding_data/ + - data_file: /opt/tiger/tanyue/highlight_sft_smallvlm/data/qvhighlights/train_w_cot_aligned.json + data_type: llava_video + dataset_type: qwen3vl_video + image_dir: /mnt/bn/strategy-mllm-train/common/temporal_grounding_data/ + max_length: 8192 +MODEL_CONFIG: + architecture: AutoModelForImageTextToText + attn_implementation: flash_attention_2 + name_or_path: Qwen/Qwen3-VL-4B-Instruct + torch_dtype: bfloat16 + tune_mm_llm: true + tune_mm_mlp: true + tune_mm_vision: false +PROCESSOR_CONFIG: + name_or_path: Qwen/Qwen3-VL-4B-Instruct + processor_class: AutoProcessor +TRAINING_CONFIG: + bf16: true + dataloader_drop_last: true + dataloader_num_workers: 32 + dataloader_pin_memory: false + dataloader_prefetch_factor: 2 + ddp_backend: null + deepspeed: + bf16: + enabled: auto + fp16: + enabled: auto + hysteresis: 2 + initial_scale_power: 16 + loss_scale: 0 + loss_scale_window: 1000 + min_loss_scale: 1 + gradient_accumulation_steps: auto + gradient_clipping: auto + train_batch_size: auto + train_micro_batch_size_per_gpu: auto + zero_optimization: + allgather_bucket_size: 536870912 + contiguous_gradients: true + overlap_comm: true + reduce_bucket_size: 536870912 + stage: 2 + gradient_accumulation_steps: 4 + gradient_checkpointing: true + learning_rate: 1.0e-05 + logging_steps: 1 + lr_scheduler_type: cosine + max_grad_norm: 1 + num_train_epochs: 4 + output_dir: /mnt/bn/strategy-mllm-train/user/tanyue/models/posttrain_models/qwen3vl_4b_cha_act_qvh_w_cot_aligned/ + per_device_eval_batch_size: 8 + per_device_train_batch_size: 8 + report_to: tensorboard + save_only_model: false + save_safetensors: true + save_steps: 1000 + save_strategy: epoch + save_total_limit: 4 + sequence_parallel_size: 8 + tf32: true + torch_empty_cache_steps: 627 + use_online_length_grouped_dataloader: true + warmup_ratio: 0.3 + weight_decay: 0.1 +_PARAMETERS_: true diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/added_tokens.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/chat_template.jinja b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/generation_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..e7137b5a305cb94582cf3a1c9b47e4046550e24d --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00003.safetensors", + "model.language_model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.norm.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00003-of-00003.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00003-of-00003.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00003-of-00003.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00003-of-00003.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00003.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.merger.norm.bias": "model-00002-of-00003.safetensors", + "model.visual.merger.norm.weight": "model-00002-of-00003.safetensors", + "model.visual.patch_embed.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.patch_embed.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.pos_embed.weight": "model-00002-of-00003.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/processor_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/special_tokens_map.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/tokenizer_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_50/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/added_tokens.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/chat_template.jinja b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/generation_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..c76e8b93137d1207651dbd8c4d7d2319871ab838 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00003.safetensors", + "model.language_model.embed_tokens.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.norm.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00003-of-00003.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00003.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.merger.norm.bias": "model-00001-of-00003.safetensors", + "model.visual.merger.norm.weight": "model-00002-of-00003.safetensors", + "model.visual.patch_embed.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.patch_embed.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.pos_embed.weight": "model-00001-of-00003.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/processor_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/special_tokens_map.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/tokenizer_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_60/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/added_tokens.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/chat_template.jinja b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/generation_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..c9a96552d13d71b8a8a772ccd4986306717788f5 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/processor_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/special_tokens_map.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/tokenizer_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_70/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/added_tokens.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/chat_template.jinja b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/generation_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..406ab750d90a6f18c32157d4cbf82514d196a6a4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/processor_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/special_tokens_map.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/tokenizer_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_80/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/added_tokens.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/chat_template.jinja b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/generation_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..e71d9012293d0a0eddd89d936c94f9d651478924 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/processor_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/special_tokens_map.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/tokenizer_config.json b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_multimath_rl_50k/global_step_97/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..851abb0686318c5f90a2fae6c8bcdc56cdde52c7 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_10/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..01c55fb76fbe8eb8e5cfc20ec964a1c32d110ba2 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_20/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..7707428760c80c973a209aeab52f87300b714621 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_30/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..184d0b64b02f89bb49e20fdf5cb8ee037463eee8 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_40/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..e55978422a454cf758459001385e472bd7caa9cc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_50/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..c5cf326cbf938e590d9c63e1af6908f0fbb5bee1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath/global_step_60/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..670060d148764604715957eb8510867bb61a1d98 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_10k/global_step_19/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5009b2222e39f2ee0065aa745a2666d75bb586aa --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_60/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5883667965bb2ea417056585e2c5dbc22a5439f3 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00003.safetensors", + "model.language_model.embed_tokens.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.language_model.norm.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00003-of-00003.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00003-of-00003.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00003-of-00003.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00003-of-00003.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00002-of-00003.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00003.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00003.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00002-of-00003.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00002-of-00003.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00001-of-00003.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00002-of-00003.safetensors", + "model.visual.merger.norm.bias": "model-00002-of-00003.safetensors", + "model.visual.merger.norm.weight": "model-00002-of-00003.safetensors", + "model.visual.patch_embed.proj.bias": "model-00002-of-00003.safetensors", + "model.visual.patch_embed.proj.weight": "model-00002-of-00003.safetensors", + "model.visual.pos_embed.weight": "model-00002-of-00003.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_70/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..8948a37109d78ad3aade0fb4e2eadf6b4ed8f93f --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_80/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..e8b07eeabd983a1946856a684b16e3dafd61ed33 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_90/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..4ba742cc4b70839b2a53b2f7851f57206b4a60ab --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k/global_step_98/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/generation_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..8458f29aec2209e3f63ca59bca95814310a80de1 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0.dev0" +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/model.safetensors.index.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..7fb0e3c49e909362bb88de47ca062838c123c4a0 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/model.safetensors.index.json @@ -0,0 +1,722 @@ +{ + "metadata": { + "total_parameters": 4826771968, + "total_size": 9653543936 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00002.safetensors", + "model.language_model.embed_tokens.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/processor_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a4fe483a685ede297970ea7a13145d5aabe63a1c --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/processor_config.json @@ -0,0 +1,85 @@ +{ + "image_processor": { + "crop_size": null, + "data_format": "channels_first", + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_seq_length": null, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 + }, + "processor_class": "Qwen3VLProcessor", + "video_processor": { + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "return_tensors": null, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/special_tokens_map.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ac23c0aaa2434523c494330aeb79c58395378103 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/tokenizer_config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fec7f182135c384a08ea2fc9635566ca79c45afc --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_30/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/added_tokens.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..b54f9135e44c1e81047e8d05cb027af8bc039eed --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/chat_template.jinja b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..124386803f142761528f710e77ae483f5f8c4fc4 --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/config.json b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fa428720af4bb46e922d1d80535378a7a55db8dd --- /dev/null +++ b/posttrain_models/qwen3vl_4b_ntr_multimath_50k_global_step_80_multimath_rl_50k/global_step_40/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "dtype": "float32", + "eos_token_id": 151645, + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151643, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "dtype": "float32", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file