Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- args.json +484 -0
- chat_template.jinja +154 -0
- config.json +110 -0
- generation_config.json +9 -0
- infer_result/20260522-092950.jsonl +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +768 -0
- preprocessor_config.json +21 -0
- processor_config.json +63 -0
- run_deploy.log +138 -0
- tokenizer.json +3 -0
- tokenizer_config.json +32 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
args.json
ADDED
|
@@ -0,0 +1,484 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/workspace/generative-gongyi-generation/grpo/result-1-grpo/20260521/v3-20260521-151950",
|
| 3 |
+
"per_device_train_batch_size": 4,
|
| 4 |
+
"num_train_epochs": 8.0,
|
| 5 |
+
"max_steps": -1,
|
| 6 |
+
"learning_rate": 5e-06,
|
| 7 |
+
"lr_scheduler_type": "cosine",
|
| 8 |
+
"lr_scheduler_kwargs": null,
|
| 9 |
+
"warmup_steps": 0,
|
| 10 |
+
"optim": "adamw_torch_fused",
|
| 11 |
+
"optim_args": null,
|
| 12 |
+
"weight_decay": 0.1,
|
| 13 |
+
"adam_beta1": 0.9,
|
| 14 |
+
"adam_beta2": 0.95,
|
| 15 |
+
"adam_epsilon": 1e-08,
|
| 16 |
+
"optim_target_modules": null,
|
| 17 |
+
"gradient_accumulation_steps": 2,
|
| 18 |
+
"average_tokens_across_devices": true,
|
| 19 |
+
"max_grad_norm": 1.0,
|
| 20 |
+
"label_smoothing_factor": 0.0,
|
| 21 |
+
"bf16": true,
|
| 22 |
+
"fp16": false,
|
| 23 |
+
"bf16_full_eval": false,
|
| 24 |
+
"fp16_full_eval": false,
|
| 25 |
+
"tf32": null,
|
| 26 |
+
"gradient_checkpointing": true,
|
| 27 |
+
"gradient_checkpointing_kwargs": null,
|
| 28 |
+
"torch_compile": false,
|
| 29 |
+
"torch_compile_backend": null,
|
| 30 |
+
"torch_compile_mode": null,
|
| 31 |
+
"use_liger_kernel": false,
|
| 32 |
+
"liger_kernel_config": null,
|
| 33 |
+
"use_cache": false,
|
| 34 |
+
"neftune_noise_alpha": null,
|
| 35 |
+
"torch_empty_cache_steps": null,
|
| 36 |
+
"auto_find_batch_size": false,
|
| 37 |
+
"logging_strategy": "steps",
|
| 38 |
+
"logging_steps": 5,
|
| 39 |
+
"logging_first_step": true,
|
| 40 |
+
"log_on_each_node": true,
|
| 41 |
+
"logging_nan_inf_filter": true,
|
| 42 |
+
"include_num_input_tokens_seen": false,
|
| 43 |
+
"log_level": "passive",
|
| 44 |
+
"log_level_replica": "warning",
|
| 45 |
+
"disable_tqdm": null,
|
| 46 |
+
"report_to": [
|
| 47 |
+
"tensorboard"
|
| 48 |
+
],
|
| 49 |
+
"run_name": "/workspace/generative-gongyi-generation/grpo/result-1-grpo/20260521/v3-20260521-151950",
|
| 50 |
+
"project": "huggingface",
|
| 51 |
+
"trackio_space_id": "trackio",
|
| 52 |
+
"eval_strategy": "steps",
|
| 53 |
+
"eval_steps": 20.0,
|
| 54 |
+
"eval_delay": 0,
|
| 55 |
+
"per_device_eval_batch_size": 4,
|
| 56 |
+
"prediction_loss_only": false,
|
| 57 |
+
"eval_on_start": false,
|
| 58 |
+
"eval_do_concat_batches": true,
|
| 59 |
+
"eval_use_gather_object": false,
|
| 60 |
+
"eval_accumulation_steps": null,
|
| 61 |
+
"include_for_metrics": [],
|
| 62 |
+
"batch_eval_metrics": false,
|
| 63 |
+
"save_only_model": false,
|
| 64 |
+
"save_strategy": "steps",
|
| 65 |
+
"save_steps": 20.0,
|
| 66 |
+
"save_on_each_node": false,
|
| 67 |
+
"save_total_limit": 2,
|
| 68 |
+
"enable_jit_checkpoint": false,
|
| 69 |
+
"push_to_hub": false,
|
| 70 |
+
"hub_token": null,
|
| 71 |
+
"hub_private_repo": null,
|
| 72 |
+
"hub_model_id": null,
|
| 73 |
+
"hub_strategy": "every_save",
|
| 74 |
+
"hub_always_push": false,
|
| 75 |
+
"hub_revision": null,
|
| 76 |
+
"load_best_model_at_end": false,
|
| 77 |
+
"metric_for_best_model": "reward",
|
| 78 |
+
"greater_is_better": true,
|
| 79 |
+
"ignore_data_skip": false,
|
| 80 |
+
"restore_callback_states_from_checkpoint": false,
|
| 81 |
+
"full_determinism": false,
|
| 82 |
+
"seed": 42,
|
| 83 |
+
"data_seed": 42,
|
| 84 |
+
"use_cpu": false,
|
| 85 |
+
"accelerator_config": {
|
| 86 |
+
"dispatch_batches": false
|
| 87 |
+
},
|
| 88 |
+
"parallelism_config": null,
|
| 89 |
+
"dataloader_drop_last": false,
|
| 90 |
+
"dataloader_num_workers": 4,
|
| 91 |
+
"dataloader_pin_memory": true,
|
| 92 |
+
"dataloader_persistent_workers": false,
|
| 93 |
+
"dataloader_prefetch_factor": null,
|
| 94 |
+
"remove_unused_columns": false,
|
| 95 |
+
"label_names": null,
|
| 96 |
+
"train_sampling_strategy": "random",
|
| 97 |
+
"length_column_name": "length",
|
| 98 |
+
"ddp_find_unused_parameters": null,
|
| 99 |
+
"ddp_bucket_cap_mb": null,
|
| 100 |
+
"ddp_broadcast_buffers": null,
|
| 101 |
+
"ddp_backend": null,
|
| 102 |
+
"ddp_timeout": 18000000,
|
| 103 |
+
"fsdp": [],
|
| 104 |
+
"fsdp_config": null,
|
| 105 |
+
"deepspeed": null,
|
| 106 |
+
"debug": null,
|
| 107 |
+
"skip_memory_metrics": true,
|
| 108 |
+
"do_train": false,
|
| 109 |
+
"do_eval": false,
|
| 110 |
+
"do_predict": false,
|
| 111 |
+
"resume_from_checkpoint": null,
|
| 112 |
+
"warmup_ratio": 0.0,
|
| 113 |
+
"logging_dir": "/workspace/generative-gongyi-generation/grpo/result-1-grpo/20260521/v3-20260521-151950/runs",
|
| 114 |
+
"local_rank": 0,
|
| 115 |
+
"sortish_sampler": false,
|
| 116 |
+
"predict_with_generate": false,
|
| 117 |
+
"generation_max_length": null,
|
| 118 |
+
"generation_num_beams": null,
|
| 119 |
+
"generation_config": null,
|
| 120 |
+
"tuner_backend": "peft",
|
| 121 |
+
"vit_gradient_checkpointing": false,
|
| 122 |
+
"router_aux_loss_coef": 0.0,
|
| 123 |
+
"enable_dft_loss": false,
|
| 124 |
+
"enable_channel_loss": false,
|
| 125 |
+
"safe_serialization": true,
|
| 126 |
+
"max_shard_size": "5GB",
|
| 127 |
+
"check_model": true,
|
| 128 |
+
"acc_strategy": "token",
|
| 129 |
+
"train_dataloader_shuffle": true,
|
| 130 |
+
"group_by_length": false,
|
| 131 |
+
"max_epochs": null,
|
| 132 |
+
"aligner_lr": null,
|
| 133 |
+
"vit_lr": null,
|
| 134 |
+
"use_logits_to_keep": null,
|
| 135 |
+
"ds3_gather_for_generation": true,
|
| 136 |
+
"resume_only_model": false,
|
| 137 |
+
"optimizer": null,
|
| 138 |
+
"loss_type": "grpo",
|
| 139 |
+
"eval_metric": null,
|
| 140 |
+
"callbacks": [],
|
| 141 |
+
"early_stop_interval": 5,
|
| 142 |
+
"eval_use_evalscope": false,
|
| 143 |
+
"eval_dataset": [],
|
| 144 |
+
"eval_dataset_args": null,
|
| 145 |
+
"eval_limit": null,
|
| 146 |
+
"eval_generation_config": null,
|
| 147 |
+
"extra_eval_args": null,
|
| 148 |
+
"tuner_type": "lora",
|
| 149 |
+
"use_galore": false,
|
| 150 |
+
"galore_target_modules": null,
|
| 151 |
+
"galore_rank": 128,
|
| 152 |
+
"galore_update_proj_gap": 50,
|
| 153 |
+
"galore_scale": 1.0,
|
| 154 |
+
"galore_proj_type": "std",
|
| 155 |
+
"galore_optim_per_parameter": false,
|
| 156 |
+
"galore_with_embedding": false,
|
| 157 |
+
"galore_quantization": false,
|
| 158 |
+
"galore_proj_quant": false,
|
| 159 |
+
"galore_proj_bits": 4,
|
| 160 |
+
"galore_proj_group_size": 256,
|
| 161 |
+
"galore_cos_threshold": 0.4,
|
| 162 |
+
"galore_gamma_proj": 2,
|
| 163 |
+
"galore_queue_size": 5,
|
| 164 |
+
"lisa_activated_layers": 0,
|
| 165 |
+
"lisa_step_interval": 20,
|
| 166 |
+
"use_flash_ckpt": false,
|
| 167 |
+
"use_ray": false,
|
| 168 |
+
"ray_exp_name": null,
|
| 169 |
+
"device_groups": null,
|
| 170 |
+
"model": "/workspace/model/Qwen3.5-9B",
|
| 171 |
+
"model_type": "qwen3_5",
|
| 172 |
+
"model_revision": null,
|
| 173 |
+
"task_type": "causal_lm",
|
| 174 |
+
"torch_dtype": "bfloat16",
|
| 175 |
+
"attn_impl": null,
|
| 176 |
+
"experts_impl": null,
|
| 177 |
+
"new_special_tokens": [],
|
| 178 |
+
"num_labels": null,
|
| 179 |
+
"problem_type": null,
|
| 180 |
+
"rope_scaling": null,
|
| 181 |
+
"device_map": null,
|
| 182 |
+
"max_memory": {},
|
| 183 |
+
"max_model_len": null,
|
| 184 |
+
"local_repo_path": null,
|
| 185 |
+
"init_strategy": null,
|
| 186 |
+
"template": "qwen3_5",
|
| 187 |
+
"system": null,
|
| 188 |
+
"max_length": 10240,
|
| 189 |
+
"truncation_strategy": "left",
|
| 190 |
+
"max_pixels": null,
|
| 191 |
+
"agent_template": null,
|
| 192 |
+
"norm_bbox": null,
|
| 193 |
+
"use_chat_template": true,
|
| 194 |
+
"padding_side": "right",
|
| 195 |
+
"padding_free": false,
|
| 196 |
+
"loss_scale": "last_round",
|
| 197 |
+
"sequence_parallel_size": 1,
|
| 198 |
+
"template_backend": "swift",
|
| 199 |
+
"response_prefix": null,
|
| 200 |
+
"enable_thinking": null,
|
| 201 |
+
"add_non_thinking_prefix": true,
|
| 202 |
+
"dataset": [
|
| 203 |
+
"/workspace/generative-gongyi-generation/gongyi_prepare/data/1_grpo_train.jsonl"
|
| 204 |
+
],
|
| 205 |
+
"val_dataset": [
|
| 206 |
+
"/workspace/generative-gongyi-generation/gongyi_prepare/data/1_grpo_val.jsonl"
|
| 207 |
+
],
|
| 208 |
+
"cached_dataset": [],
|
| 209 |
+
"cached_val_dataset": [],
|
| 210 |
+
"split_dataset_ratio": 0.0,
|
| 211 |
+
"dataset_num_proc": 1,
|
| 212 |
+
"load_from_cache_file": false,
|
| 213 |
+
"dataset_shuffle": true,
|
| 214 |
+
"val_dataset_shuffle": false,
|
| 215 |
+
"streaming": false,
|
| 216 |
+
"interleave_prob": null,
|
| 217 |
+
"stopping_strategy": "first_exhausted",
|
| 218 |
+
"shuffle_buffer_size": 1000,
|
| 219 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 220 |
+
"columns": {},
|
| 221 |
+
"strict": false,
|
| 222 |
+
"disable_auto_column_mapping": false,
|
| 223 |
+
"model_name": null,
|
| 224 |
+
"model_author": null,
|
| 225 |
+
"custom_dataset_info": [],
|
| 226 |
+
"quant_method": null,
|
| 227 |
+
"quant_bits": null,
|
| 228 |
+
"hqq_axis": null,
|
| 229 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 230 |
+
"bnb_4bit_quant_type": "nf4",
|
| 231 |
+
"bnb_4bit_use_double_quant": true,
|
| 232 |
+
"bnb_4bit_quant_storage": null,
|
| 233 |
+
"max_new_tokens": 3072,
|
| 234 |
+
"temperature": 0.7,
|
| 235 |
+
"top_k": -1,
|
| 236 |
+
"top_p": 1.0,
|
| 237 |
+
"repetition_penalty": 1.0,
|
| 238 |
+
"num_beams": 1,
|
| 239 |
+
"stream": false,
|
| 240 |
+
"stop_words": [],
|
| 241 |
+
"logprobs": false,
|
| 242 |
+
"top_logprobs": null,
|
| 243 |
+
"structured_outputs_regex": null,
|
| 244 |
+
"adapters": [
|
| 245 |
+
"/workspace/generative-gongyi-generation/sft/result-1-sft/20260515/v5-20260518-143925/checkpoint-792"
|
| 246 |
+
],
|
| 247 |
+
"external_plugins": [
|
| 248 |
+
"/workspace/generative-gongyi-generation/grpo/grpo_sequence_reward.py"
|
| 249 |
+
],
|
| 250 |
+
"custom_register_path": [],
|
| 251 |
+
"model_kwargs": {},
|
| 252 |
+
"enable_npu_model_patch": true,
|
| 253 |
+
"load_args": false,
|
| 254 |
+
"load_data_args": false,
|
| 255 |
+
"packing": false,
|
| 256 |
+
"packing_length": null,
|
| 257 |
+
"packing_num_proc": 1,
|
| 258 |
+
"lazy_tokenize": true,
|
| 259 |
+
"use_hf": false,
|
| 260 |
+
"ignore_args_error": false,
|
| 261 |
+
"use_swift_lora": false,
|
| 262 |
+
"freeze_parameters": [],
|
| 263 |
+
"freeze_parameters_regex": null,
|
| 264 |
+
"freeze_parameters_ratio": 0.0,
|
| 265 |
+
"trainable_parameters": [],
|
| 266 |
+
"trainable_parameters_regex": null,
|
| 267 |
+
"freeze_llm": false,
|
| 268 |
+
"freeze_vit": true,
|
| 269 |
+
"freeze_aligner": true,
|
| 270 |
+
"target_modules": [
|
| 271 |
+
"all-linear"
|
| 272 |
+
],
|
| 273 |
+
"target_regex": null,
|
| 274 |
+
"target_parameters": null,
|
| 275 |
+
"modules_to_save": [],
|
| 276 |
+
"lora_rank": 8,
|
| 277 |
+
"lora_alpha": 32,
|
| 278 |
+
"lora_dropout": 0.05,
|
| 279 |
+
"lora_bias": "none",
|
| 280 |
+
"lora_dtype": null,
|
| 281 |
+
"lorap_lr_ratio": null,
|
| 282 |
+
"use_rslora": false,
|
| 283 |
+
"use_dora": false,
|
| 284 |
+
"lora_ga_batch_size": 2,
|
| 285 |
+
"lora_ga_iters": 2,
|
| 286 |
+
"lora_ga_max_length": 1024,
|
| 287 |
+
"lora_ga_direction": "ArB2r",
|
| 288 |
+
"lora_ga_scale": "stable",
|
| 289 |
+
"lora_ga_stable_gamma": 16,
|
| 290 |
+
"init_weights": true,
|
| 291 |
+
"fourier_n_frequency": 2000,
|
| 292 |
+
"fourier_scaling": 300.0,
|
| 293 |
+
"boft_block_size": 4,
|
| 294 |
+
"boft_block_num": 0,
|
| 295 |
+
"boft_n_butterfly_factor": 1,
|
| 296 |
+
"boft_dropout": 0.0,
|
| 297 |
+
"vera_rank": 256,
|
| 298 |
+
"vera_projection_prng_key": 0,
|
| 299 |
+
"vera_dropout": 0.0,
|
| 300 |
+
"vera_d_initial": 0.1,
|
| 301 |
+
"adapter_act": "gelu",
|
| 302 |
+
"adapter_length": 128,
|
| 303 |
+
"adalora_target_r": 8,
|
| 304 |
+
"adalora_init_r": 12,
|
| 305 |
+
"adalora_tinit": 0,
|
| 306 |
+
"adalora_tfinal": 0,
|
| 307 |
+
"adalora_deltaT": 1,
|
| 308 |
+
"adalora_beta1": 0.85,
|
| 309 |
+
"adalora_beta2": 0.85,
|
| 310 |
+
"adalora_orth_reg_weight": 0.5,
|
| 311 |
+
"llamapro_num_new_blocks": 4,
|
| 312 |
+
"llamapro_num_groups": null,
|
| 313 |
+
"reft_layer_key": null,
|
| 314 |
+
"reft_layers": null,
|
| 315 |
+
"reft_rank": 4,
|
| 316 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 317 |
+
"reft_args": null,
|
| 318 |
+
"swanlab_token": null,
|
| 319 |
+
"swanlab_project": "ms-swift",
|
| 320 |
+
"swanlab_workspace": null,
|
| 321 |
+
"swanlab_exp_name": null,
|
| 322 |
+
"swanlab_notification_method": null,
|
| 323 |
+
"swanlab_webhook_url": null,
|
| 324 |
+
"swanlab_secret": null,
|
| 325 |
+
"swanlab_sender_email": null,
|
| 326 |
+
"swanlab_receiver_email": null,
|
| 327 |
+
"swanlab_smtp_server": null,
|
| 328 |
+
"swanlab_smtp_port": null,
|
| 329 |
+
"swanlab_email_language": "zh",
|
| 330 |
+
"swanlab_mode": "cloud",
|
| 331 |
+
"add_version": true,
|
| 332 |
+
"create_checkpoint_symlink": false,
|
| 333 |
+
"zero_hpz_partition_size": null,
|
| 334 |
+
"deepspeed_autotp_size": null,
|
| 335 |
+
"reward_model": null,
|
| 336 |
+
"reward_adapters": [],
|
| 337 |
+
"reward_model_type": null,
|
| 338 |
+
"reward_model_revision": null,
|
| 339 |
+
"reward_template": null,
|
| 340 |
+
"num_ppo_epochs": 4,
|
| 341 |
+
"whiten_rewards": false,
|
| 342 |
+
"kl_coef": 0.05,
|
| 343 |
+
"cliprange": 0.2,
|
| 344 |
+
"vf_coef": 0.1,
|
| 345 |
+
"cliprange_value": 0.2,
|
| 346 |
+
"gamma": 1.0,
|
| 347 |
+
"lam": 0.95,
|
| 348 |
+
"num_mini_batches": 1,
|
| 349 |
+
"local_rollout_forward_batch_size": 64,
|
| 350 |
+
"num_sample_generations": 10,
|
| 351 |
+
"response_length": 3072,
|
| 352 |
+
"missing_eos_penalty": null,
|
| 353 |
+
"vllm_gpu_memory_utilization": 0.5,
|
| 354 |
+
"vllm_tensor_parallel_size": 1,
|
| 355 |
+
"vllm_pipeline_parallel_size": 1,
|
| 356 |
+
"vllm_enable_expert_parallel": false,
|
| 357 |
+
"vllm_max_num_seqs": null,
|
| 358 |
+
"vllm_max_model_len": 10240,
|
| 359 |
+
"vllm_disable_custom_all_reduce": true,
|
| 360 |
+
"vllm_enforce_eager": false,
|
| 361 |
+
"vllm_limit_mm_per_prompt": null,
|
| 362 |
+
"vllm_max_lora_rank": 16,
|
| 363 |
+
"vllm_enable_prefix_caching": true,
|
| 364 |
+
"vllm_use_async_engine": null,
|
| 365 |
+
"vllm_quantization": null,
|
| 366 |
+
"vllm_reasoning_parser": null,
|
| 367 |
+
"vllm_disable_cascade_attn": false,
|
| 368 |
+
"vllm_mm_processor_cache_gb": 0.0,
|
| 369 |
+
"vllm_speculative_config": null,
|
| 370 |
+
"vllm_engine_kwargs": {},
|
| 371 |
+
"vllm_data_parallel_size": 1,
|
| 372 |
+
"use_vllm": true,
|
| 373 |
+
"vllm_mode": "colocate",
|
| 374 |
+
"vllm_enable_lora": false,
|
| 375 |
+
"vllm_server_base_url": null,
|
| 376 |
+
"vllm_server_host": null,
|
| 377 |
+
"vllm_server_port": [
|
| 378 |
+
8000
|
| 379 |
+
],
|
| 380 |
+
"vllm_server_timeout": 240.0,
|
| 381 |
+
"vllm_server_group_port": null,
|
| 382 |
+
"enable_flattened_weight_sync": true,
|
| 383 |
+
"async_generate": false,
|
| 384 |
+
"sleep_level": 1,
|
| 385 |
+
"move_model_batches": 4,
|
| 386 |
+
"offload_optimizer": false,
|
| 387 |
+
"offload_model": false,
|
| 388 |
+
"wandb_log_unique_prompts": null,
|
| 389 |
+
"generation_batch_size": null,
|
| 390 |
+
"steps_per_generation": null,
|
| 391 |
+
"epsilon": 0.2,
|
| 392 |
+
"epsilon_high": null,
|
| 393 |
+
"delta": null,
|
| 394 |
+
"cosine_min_len_value_wrong": -0.5,
|
| 395 |
+
"cosine_max_len_value_wrong": 0.0,
|
| 396 |
+
"cosine_min_len_value_correct": 1.0,
|
| 397 |
+
"cosine_max_len_value_correct": 0.5,
|
| 398 |
+
"cosine_max_len": null,
|
| 399 |
+
"repetition_n_grams": 3,
|
| 400 |
+
"repetition_max_penalty": -1.0,
|
| 401 |
+
"reward_model_plugin": null,
|
| 402 |
+
"chord_sft_dataset": [],
|
| 403 |
+
"chord_sft_per_device_train_batch_size": null,
|
| 404 |
+
"chord_enable_phi_function": false,
|
| 405 |
+
"chord_mu_warmup_steps": null,
|
| 406 |
+
"chord_mu_decay_steps": null,
|
| 407 |
+
"chord_mu_peak": null,
|
| 408 |
+
"chord_mu_valley": null,
|
| 409 |
+
"sync_ref_model": false,
|
| 410 |
+
"ref_model_sync_steps": 512,
|
| 411 |
+
"ref_model_mixup_alpha": 0.6,
|
| 412 |
+
"multi_turn_scheduler": null,
|
| 413 |
+
"max_turns": null,
|
| 414 |
+
"completion_length_limit_scope": "per_round",
|
| 415 |
+
"vllm_server_pass_dataset": false,
|
| 416 |
+
"dynamic_sample": false,
|
| 417 |
+
"max_resample_times": 3,
|
| 418 |
+
"overlong_filter": false,
|
| 419 |
+
"soft_max_length": null,
|
| 420 |
+
"soft_cache_length": null,
|
| 421 |
+
"scale_rewards": "group",
|
| 422 |
+
"log_entropy": false,
|
| 423 |
+
"top_entropy_quantile": 1.0,
|
| 424 |
+
"importance_sampling_level": "token",
|
| 425 |
+
"tau_pos": 1.0,
|
| 426 |
+
"tau_neg": 1.05,
|
| 427 |
+
"advantage_estimator": "grpo",
|
| 428 |
+
"kl_in_reward": false,
|
| 429 |
+
"real_tau": 0.5,
|
| 430 |
+
"num_generations_eval": 8,
|
| 431 |
+
"rollout_importance_sampling_mode": null,
|
| 432 |
+
"rollout_importance_sampling_threshold": 2.0,
|
| 433 |
+
"log_rollout_offpolicy_metrics": false,
|
| 434 |
+
"off_policy_sequence_mask_delta": null,
|
| 435 |
+
"num_generations": 8,
|
| 436 |
+
"reward_funcs": [
|
| 437 |
+
"sequence_order_reward"
|
| 438 |
+
],
|
| 439 |
+
"reward_weights": null,
|
| 440 |
+
"log_completions": true,
|
| 441 |
+
"num_iterations": 1,
|
| 442 |
+
"teacher_model": null,
|
| 443 |
+
"teacher_adapters": [],
|
| 444 |
+
"teacher_model_type": null,
|
| 445 |
+
"teacher_model_revision": null,
|
| 446 |
+
"teacher_deepspeed": null,
|
| 447 |
+
"teacher_model_server": null,
|
| 448 |
+
"rlhf_type": "grpo",
|
| 449 |
+
"ref_model": null,
|
| 450 |
+
"ref_adapters": [],
|
| 451 |
+
"ref_model_type": null,
|
| 452 |
+
"ref_model_revision": null,
|
| 453 |
+
"beta": 0.04,
|
| 454 |
+
"label_smoothing": 0,
|
| 455 |
+
"max_completion_length": 3072,
|
| 456 |
+
"rpo_alpha": null,
|
| 457 |
+
"ld_alpha": null,
|
| 458 |
+
"discopop_tau": 0.05,
|
| 459 |
+
"loss_weights": null,
|
| 460 |
+
"cpo_alpha": 1.0,
|
| 461 |
+
"simpo_gamma": 1,
|
| 462 |
+
"desirable_weight": 1.0,
|
| 463 |
+
"undesirable_weight": 1.0,
|
| 464 |
+
"center_rewards_coefficient": null,
|
| 465 |
+
"sft_alpha": 0,
|
| 466 |
+
"lmbda": 0.5,
|
| 467 |
+
"seq_kd": false,
|
| 468 |
+
"gkd_logits_topk": null,
|
| 469 |
+
"offload_teacher_model": false,
|
| 470 |
+
"swift_version": "4.2.1",
|
| 471 |
+
"ckpt_dir": "/workspace/generative-gongyi-generation/sft/result-1-sft/20260515/v5-20260518-143925/checkpoint-792",
|
| 472 |
+
"rank": 0,
|
| 473 |
+
"global_world_size": 4,
|
| 474 |
+
"local_world_size": 4,
|
| 475 |
+
"model_suffix": "Qwen3.5-9B",
|
| 476 |
+
"model_info": "ModelInfo(model_type='qwen3_5', model_dir='/workspace/model/Qwen3.5-9B', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
|
| 477 |
+
"model_meta": "ModelMeta(model_type='qwen3_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3.5-0.8B', hf_model_id='Qwen/Qwen3.5-0.8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-2B', hf_model_id='Qwen/Qwen3.5-2B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-4B', hf_model_id='Qwen/Qwen3.5-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-9B', hf_model_id='Qwen/Qwen3.5-9B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-27B', hf_model_id='Qwen/Qwen3.5-27B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-27B-FP8', hf_model_id='Qwen/Qwen3.5-27B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-0.8B-Base', hf_model_id='Qwen/Qwen3.5-0.8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-2B-Base', hf_model_id='Qwen/Qwen3.5-2B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-4B-Base', hf_model_id='Qwen/Qwen3.5-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-9B-Base', hf_model_id='Qwen/Qwen3.5-9B-Base', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_5', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3.6-27B', hf_model_id='Qwen/Qwen3.6-27B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.6-27B-FP8', hf_model_id='Qwen/Qwen3.6-27B-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_5', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen3_5Loader'>, template='qwen3_5', model_arch=MultiModelKeys(arch_name='qwen2_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'], vision_tower=['model.visual'], generator=[]), mcore_model_type=None, architectures=['Qwen3_5ForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=5.0.0.dev', 'qwen_vl_utils>=0.0.14', 'decord'], tags=[])",
|
| 478 |
+
"model_dir": "/workspace/model/Qwen3.5-9B",
|
| 479 |
+
"template_meta": "QwenTemplateMeta(template_type='qwen3_5', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.qwen.Qwen3_5Template'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='qwen3_5', is_thinking=True, thinking_prefix='<think>\\n', non_thinking_prefix='<think>\\n\\n</think>\\n\\n', history_thinking_prefix='')",
|
| 480 |
+
"_val_dataset_exists": true,
|
| 481 |
+
"hub": "<class 'swift.hub.hub.MSHub'>",
|
| 482 |
+
"evaluation_strategy": "steps",
|
| 483 |
+
"training_args": "GRPOConfig(output_dir='/workspace/generative-gongyi-generation/grpo/result-1-grpo/20260521/v3-20260521-151950', per_device_train_batch_size=4, num_train_epochs=8.0, max_steps=-1, learning_rate=5e-06, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_steps=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, optim_target_modules=None, gradient_accumulation_steps=2, average_tokens_across_devices=None, max_grad_norm=1.0, label_smoothing_factor=0.0, bf16=True, fp16=False, bf16_full_eval=False, fp16_full_eval=False, tf32=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, use_liger_kernel=False, liger_kernel_config=None, use_cache=False, neftune_noise_alpha=None, torch_empty_cache_steps=None, auto_find_batch_size=False, logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_steps=5, logging_first_step=True, log_on_each_node=True, logging_nan_inf_filter=True, include_num_input_tokens_seen=None, log_level='passive', log_level_replica='warning', disable_tqdm=False, report_to=['tensorboard'], run_name='/workspace/generative-gongyi-generation/grpo/result-1-grpo/20260521/v3-20260521-151950', project='huggingface', trackio_space_id='trackio', eval_strategy=<IntervalStrategy.STEPS: 'steps'>, eval_steps=20, eval_delay=0, per_device_eval_batch_size=4, prediction_loss_only=False, eval_on_start=False, eval_do_concat_batches=True, eval_use_gather_object=False, eval_accumulation_steps=None, include_for_metrics=[], batch_eval_metrics=False, save_only_model=False, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=20, save_on_each_node=False, save_total_limit=2, enable_jit_checkpoint=False, push_to_hub=False, hub_token=None, hub_private_repo=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_always_push=False, hub_revision=None, load_best_model_at_end=False, metric_for_best_model='reward', greater_is_better=True, ignore_data_skip=False, restore_callback_states_from_checkpoint=False, full_determinism=False, seed=42, data_seed=42, use_cpu=False, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, dataloader_drop_last=True, dataloader_num_workers=4, dataloader_pin_memory=True, dataloader_persistent_workers=False, dataloader_prefetch_factor=2, remove_unused_columns=False, label_names=None, train_sampling_strategy='random', length_column_name='length', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, ddp_backend=None, ddp_timeout=18000000, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, deepspeed=None, debug=[], skip_memory_metrics=True, do_train=False, do_eval=True, do_predict=False, resume_from_checkpoint=None, warmup_ratio=0.0, logging_dir='/workspace/generative-gongyi-generation/grpo/result-1-grpo/20260521/v3-20260521-151950/runs', local_rank=0, model_init_kwargs=None, disable_dropout=False, cast_lm_head_to_fp32=False, num_generations=8, num_generations_eval=8, max_completion_length=3072, ds3_gather_for_generation=True, shuffle_dataset=True, generation_batch_size=32, steps_per_generation=2, temperature=0.7, top_p=1.0, top_k=-1, min_p=None, generation_kwargs=None, chat_template_kwargs=None, repetition_penalty=1.0, use_transformers_paged=False, cache_implementation=None, use_vllm=True, vllm_mode='colocate', vllm_model_impl='vllm', vllm_enable_sleep_mode=False, vllm_guided_decoding_regex=None, vllm_server_base_url=None, vllm_server_host=None, vllm_server_port=[8000], vllm_server_timeout=240.0, vllm_gpu_memory_utilization=0.5, vllm_max_model_length=None, vllm_tensor_parallel_size=1, beta=0.04, num_iterations=1, epsilon=0.2, delta=None, epsilon_high=None, sapo_temperature_neg=1.05, sapo_temperature_pos=1.0, importance_sampling_level='token', reward_weights=None, scale_rewards='group', loss_type='grpo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, top_entropy_quantile=1.0, use_liger_loss=None, vllm_importance_sampling_correction=True, vllm_importance_sampling_mode='sequence_mask', vllm_importance_sampling_cap=3.0, use_bias_correction_kl=False, log_completions=True, num_completions_to_print=None, log_unique_prompts=False, max_prompt_length=None, wandb_log_unique_prompts=None, tuner_backend='peft', vit_gradient_checkpointing=False, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, group_by_length=False, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, resume_only_model=False, optimizer=None, eval_metric=None, callbacks=['early_stop'], early_stop_interval=5, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='lora', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False, vllm_pipeline_parallel_size=1, vllm_enable_expert_parallel=False, vllm_max_num_seqs=None, vllm_max_model_len=10240, vllm_disable_custom_all_reduce=True, vllm_enforce_eager=False, vllm_limit_mm_per_prompt=None, vllm_max_lora_rank=16, vllm_enable_prefix_caching=True, vllm_use_async_engine=None, vllm_quantization=None, vllm_reasoning_parser=None, vllm_disable_cascade_attn=False, vllm_mm_processor_cache_gb=0.0, vllm_speculative_config=None, vllm_engine_kwargs={}, vllm_data_parallel_size=1, stop_words=[], vllm_enable_lora=False, lora_rank=8, vllm_server_group_port=None, enable_flattened_weight_sync=True, async_generate=False, structured_outputs_regex=None, sleep_level=1, move_model_batches=4, offload_optimizer=False, offload_model=False, 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=3072, repetition_n_grams=3, repetition_max_penalty=-1.0, reward_model=None, reward_model_plugin=None, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, multi_turn_scheduler=None, max_turns=None, completion_length_limit_scope='per_round', vllm_server_pass_dataset=False, dynamic_sample=False, max_resample_times=3, overlong_filter=False, soft_max_length=None, soft_cache_length=None, log_entropy=False, tau_pos=1.0, tau_neg=1.05, advantage_estimator='grpo', kl_in_reward=False, real_tau=0.5, dataset_shuffle=True, rollout_importance_sampling_mode=None, rollout_importance_sampling_threshold=2.0, log_rollout_offpolicy_metrics=False, off_policy_sequence_mask_delta=None)"
|
| 484 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"hidden_size": 4096,
|
| 7 |
+
"image_token_id": 248056,
|
| 8 |
+
"model_type": "qwen3_5",
|
| 9 |
+
"text_config": {
|
| 10 |
+
"attention_bias": false,
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"attn_output_gate": true,
|
| 13 |
+
"bos_token_id": null,
|
| 14 |
+
"dtype": "bfloat16",
|
| 15 |
+
"eos_token_id": 248044,
|
| 16 |
+
"full_attention_interval": 4,
|
| 17 |
+
"head_dim": 256,
|
| 18 |
+
"hidden_act": "silu",
|
| 19 |
+
"hidden_size": 4096,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 12288,
|
| 22 |
+
"layer_types": [
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"full_attention"
|
| 55 |
+
],
|
| 56 |
+
"linear_conv_kernel_dim": 4,
|
| 57 |
+
"linear_key_head_dim": 128,
|
| 58 |
+
"linear_num_key_heads": 16,
|
| 59 |
+
"linear_num_value_heads": 32,
|
| 60 |
+
"linear_value_head_dim": 128,
|
| 61 |
+
"mamba_ssm_dtype": "float32",
|
| 62 |
+
"max_position_embeddings": 262144,
|
| 63 |
+
"mlp_only_layers": [],
|
| 64 |
+
"model_type": "qwen3_5_text",
|
| 65 |
+
"mtp_num_hidden_layers": 1,
|
| 66 |
+
"mtp_use_dedicated_embeddings": false,
|
| 67 |
+
"num_attention_heads": 16,
|
| 68 |
+
"num_hidden_layers": 32,
|
| 69 |
+
"num_key_value_heads": 4,
|
| 70 |
+
"pad_token_id": 248044,
|
| 71 |
+
"partial_rotary_factor": 0.25,
|
| 72 |
+
"rms_norm_eps": 1e-06,
|
| 73 |
+
"rope_parameters": {
|
| 74 |
+
"mrope_interleaved": true,
|
| 75 |
+
"mrope_section": [
|
| 76 |
+
11,
|
| 77 |
+
11,
|
| 78 |
+
10
|
| 79 |
+
],
|
| 80 |
+
"partial_rotary_factor": 0.25,
|
| 81 |
+
"rope_theta": 10000000,
|
| 82 |
+
"rope_type": "default"
|
| 83 |
+
},
|
| 84 |
+
"tie_word_embeddings": false,
|
| 85 |
+
"use_cache": true,
|
| 86 |
+
"vocab_size": 248320
|
| 87 |
+
},
|
| 88 |
+
"tie_word_embeddings": false,
|
| 89 |
+
"transformers_version": "5.2.0",
|
| 90 |
+
"video_token_id": 248057,
|
| 91 |
+
"vision_config": {
|
| 92 |
+
"deepstack_visual_indexes": [],
|
| 93 |
+
"depth": 27,
|
| 94 |
+
"dtype": "bfloat16",
|
| 95 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 96 |
+
"hidden_size": 1152,
|
| 97 |
+
"in_channels": 3,
|
| 98 |
+
"initializer_range": 0.02,
|
| 99 |
+
"intermediate_size": 4304,
|
| 100 |
+
"model_type": "qwen3_5",
|
| 101 |
+
"num_heads": 16,
|
| 102 |
+
"num_position_embeddings": 2304,
|
| 103 |
+
"out_hidden_size": 4096,
|
| 104 |
+
"patch_size": 16,
|
| 105 |
+
"spatial_merge_size": 2,
|
| 106 |
+
"temporal_patch_size": 2
|
| 107 |
+
},
|
| 108 |
+
"vision_end_token_id": 248054,
|
| 109 |
+
"vision_start_token_id": 248053
|
| 110 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
248044,
|
| 5 |
+
248046
|
| 6 |
+
],
|
| 7 |
+
"transformers_version": "5.2.0",
|
| 8 |
+
"use_cache": true
|
| 9 |
+
}
|
infer_result/20260522-092950.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d9c304b3a0ba2bde89efe3d7d747a9d326a19091e8b8ce48af09e3e43d2fb54
|
| 3 |
+
size 4942706120
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0087f1fd15e8e4590acb1ab1ce7ee1eafbe309996fc75a16dd8737af0d640d1
|
| 3 |
+
size 4987757928
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89a03ab87b78274d4a03905226a5b1023b13fd9dc0e066d2cf80edaa4cfd65b4
|
| 3 |
+
size 4954810240
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:941a1f235ea3aa7800268b558d659838f64077fb66f5243a06bb3979f9eb4afe
|
| 3 |
+
size 3934446832
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,768 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 9409813744,
|
| 4 |
+
"total_size": 18819627488
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 34 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 35 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 36 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 37 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 88 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 89 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 90 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 91 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 92 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 93 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 94 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 95 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 96 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 97 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 98 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 99 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 100 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 101 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 102 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 103 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 104 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 105 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 106 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 107 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 108 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 109 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 110 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 111 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 112 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 113 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 114 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 115 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 116 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 117 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 118 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 119 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 120 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 121 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 122 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 123 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 124 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 125 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 128 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 133 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 169 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00004.safetensors",
|
| 170 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 171 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
|
| 172 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
|
| 173 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
|
| 174 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 175 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 176 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 177 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 178 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 179 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 256 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 257 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 258 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 259 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 260 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 261 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 262 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 263 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 264 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 265 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 266 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 267 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 268 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 269 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 270 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 271 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 272 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 273 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 274 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 275 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 276 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 277 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 278 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 279 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 280 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 281 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 282 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 283 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 284 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 285 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 286 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 287 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 288 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 289 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 290 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 291 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 292 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 293 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 294 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 295 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 296 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 297 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 298 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 299 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 300 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 301 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 302 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 303 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 304 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 305 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 306 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 307 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 308 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 309 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 310 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 311 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 312 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 313 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 314 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 315 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 316 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 317 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 318 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 319 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 320 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 321 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 327 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 328 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 335 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 338 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 339 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 340 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 341 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 342 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 343 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 344 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 345 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 346 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 347 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 348 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 349 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 350 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 351 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 352 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 353 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 354 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 355 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 356 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 357 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 358 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 359 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 360 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 361 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 362 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 363 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 364 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 365 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 366 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 367 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 368 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 369 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 370 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 371 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 372 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 373 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 375 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 376 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 377 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 378 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 380 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 381 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 382 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 383 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 384 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 385 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 386 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 387 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 388 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 389 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 390 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 391 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 392 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 393 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 394 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 400 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 401 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 402 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 403 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 404 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 405 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 406 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 407 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 408 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 409 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 410 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 411 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 412 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 413 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 414 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 415 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 416 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 417 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 418 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 419 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 420 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 421 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 422 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 423 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 424 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 425 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 426 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 427 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 428 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 429 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 430 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 431 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 432 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 433 |
+
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 434 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 435 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 436 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 437 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 438 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 439 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 440 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 441 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 442 |
+
"model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 443 |
+
"model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 444 |
+
"model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 445 |
+
"model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 446 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 447 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 448 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 449 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 450 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 451 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 452 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 453 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 454 |
+
"model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 455 |
+
"model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 456 |
+
"model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 457 |
+
"model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 458 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 459 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 460 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 461 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 462 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 463 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 464 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 465 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 466 |
+
"model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
|
| 467 |
+
"model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
|
| 468 |
+
"model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
|
| 469 |
+
"model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
|
| 470 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 471 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 472 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 473 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 474 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 475 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 476 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 477 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 478 |
+
"model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
|
| 479 |
+
"model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
|
| 480 |
+
"model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
|
| 481 |
+
"model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
|
| 482 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 483 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 484 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 485 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 486 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 487 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 488 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 489 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 490 |
+
"model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
|
| 491 |
+
"model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
|
| 492 |
+
"model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
|
| 493 |
+
"model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
|
| 494 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 495 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 496 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 497 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 498 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 499 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 500 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 501 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 502 |
+
"model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
|
| 503 |
+
"model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
|
| 504 |
+
"model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
|
| 505 |
+
"model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
|
| 506 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 507 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 508 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 509 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 510 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 511 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 512 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 513 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 514 |
+
"model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
|
| 515 |
+
"model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
|
| 516 |
+
"model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
|
| 517 |
+
"model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
|
| 518 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 519 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 520 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 521 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 522 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 523 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 524 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 525 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 526 |
+
"model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
|
| 527 |
+
"model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
|
| 528 |
+
"model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
|
| 529 |
+
"model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
|
| 530 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 531 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 532 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 533 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 534 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 535 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 536 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 537 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 538 |
+
"model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
|
| 539 |
+
"model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
|
| 540 |
+
"model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
|
| 541 |
+
"model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
|
| 542 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 543 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 544 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 545 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 546 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 547 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 548 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 549 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 550 |
+
"model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
|
| 551 |
+
"model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
|
| 552 |
+
"model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
|
| 553 |
+
"model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
|
| 554 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 555 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 556 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 557 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 558 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 559 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 560 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 561 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 562 |
+
"model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
|
| 563 |
+
"model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
|
| 564 |
+
"model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
|
| 565 |
+
"model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
|
| 566 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 567 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 568 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 569 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 570 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 571 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 572 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 573 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 574 |
+
"model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
|
| 575 |
+
"model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
|
| 576 |
+
"model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
|
| 577 |
+
"model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
|
| 578 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 579 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 580 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 581 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 582 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 583 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 584 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 585 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 586 |
+
"model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 587 |
+
"model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 588 |
+
"model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 589 |
+
"model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 590 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 591 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 592 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 593 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 594 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 595 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 596 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 597 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 598 |
+
"model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
|
| 599 |
+
"model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
|
| 600 |
+
"model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
|
| 601 |
+
"model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
|
| 602 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 603 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 604 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 605 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 606 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 607 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 608 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 609 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 610 |
+
"model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
|
| 611 |
+
"model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
|
| 612 |
+
"model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
|
| 613 |
+
"model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
|
| 614 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 615 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 616 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 617 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 618 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 619 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 620 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 621 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 622 |
+
"model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
|
| 623 |
+
"model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
|
| 624 |
+
"model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
|
| 625 |
+
"model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
|
| 626 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 627 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 628 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 629 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 630 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 631 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 632 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 633 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 634 |
+
"model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
|
| 635 |
+
"model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
|
| 636 |
+
"model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
|
| 637 |
+
"model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
|
| 638 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 639 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 640 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 641 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 642 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 643 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 644 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 645 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 646 |
+
"model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
|
| 647 |
+
"model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
|
| 648 |
+
"model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
|
| 649 |
+
"model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
|
| 650 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 651 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 652 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 653 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 654 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 655 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 656 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 657 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 658 |
+
"model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
|
| 659 |
+
"model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
|
| 660 |
+
"model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
|
| 661 |
+
"model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
|
| 662 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 663 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 664 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 665 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 666 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 667 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 668 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 669 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 670 |
+
"model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
|
| 671 |
+
"model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
|
| 672 |
+
"model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
|
| 673 |
+
"model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
|
| 674 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 675 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 676 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 677 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 678 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 679 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 680 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 681 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 682 |
+
"model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
|
| 683 |
+
"model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
|
| 684 |
+
"model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
|
| 685 |
+
"model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
|
| 686 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 687 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 688 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 689 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 690 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 691 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 692 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 693 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 694 |
+
"model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
|
| 695 |
+
"model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
|
| 696 |
+
"model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
|
| 697 |
+
"model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
|
| 698 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 699 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 700 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 701 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 702 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 703 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 704 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 705 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 706 |
+
"model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
|
| 707 |
+
"model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
|
| 708 |
+
"model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
|
| 709 |
+
"model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
|
| 710 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 711 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 712 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 713 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 714 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 715 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 716 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 717 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 718 |
+
"model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
|
| 719 |
+
"model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
|
| 720 |
+
"model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
|
| 721 |
+
"model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
|
| 722 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 723 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 724 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 725 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 726 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 727 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 728 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 729 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 730 |
+
"model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
|
| 731 |
+
"model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
|
| 732 |
+
"model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
|
| 733 |
+
"model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
| 734 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 735 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 736 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 737 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 738 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 739 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 740 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 741 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 742 |
+
"model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
|
| 743 |
+
"model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
|
| 744 |
+
"model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
|
| 745 |
+
"model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
|
| 746 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 747 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 748 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 749 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 750 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 751 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 752 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 753 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 754 |
+
"model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
|
| 755 |
+
"model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
|
| 756 |
+
"model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
|
| 757 |
+
"model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
|
| 758 |
+
"model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 759 |
+
"model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 760 |
+
"model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 761 |
+
"model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 762 |
+
"model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
|
| 763 |
+
"model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
|
| 764 |
+
"model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
|
| 765 |
+
"model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
|
| 766 |
+
"model.visual.pos_embed.weight": "model-00004-of-00004.safetensors"
|
| 767 |
+
}
|
| 768 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"do_convert_rgb": true,
|
| 5 |
+
"do_normalize": true,
|
| 6 |
+
"do_rescale": true,
|
| 7 |
+
"do_resize": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"merge_size": 2,
|
| 20 |
+
"patch_size": 16,
|
| 21 |
+
"resample": 3,
|
| 22 |
+
"rescale_factor": 0.00392156862745098,
|
| 23 |
+
"size": {
|
| 24 |
+
"longest_edge": 16777216,
|
| 25 |
+
"shortest_edge": 65536
|
| 26 |
+
},
|
| 27 |
+
"temporal_patch_size": 2
|
| 28 |
+
},
|
| 29 |
+
"processor_class": "Qwen3VLProcessor",
|
| 30 |
+
"video_processor": {
|
| 31 |
+
"data_format": "channels_first",
|
| 32 |
+
"default_to_square": true,
|
| 33 |
+
"do_convert_rgb": true,
|
| 34 |
+
"do_normalize": true,
|
| 35 |
+
"do_rescale": true,
|
| 36 |
+
"do_resize": true,
|
| 37 |
+
"do_sample_frames": true,
|
| 38 |
+
"fps": 2,
|
| 39 |
+
"image_mean": [
|
| 40 |
+
0.5,
|
| 41 |
+
0.5,
|
| 42 |
+
0.5
|
| 43 |
+
],
|
| 44 |
+
"image_std": [
|
| 45 |
+
0.5,
|
| 46 |
+
0.5,
|
| 47 |
+
0.5
|
| 48 |
+
],
|
| 49 |
+
"max_frames": 768,
|
| 50 |
+
"merge_size": 2,
|
| 51 |
+
"min_frames": 4,
|
| 52 |
+
"patch_size": 16,
|
| 53 |
+
"resample": 3,
|
| 54 |
+
"rescale_factor": 0.00392156862745098,
|
| 55 |
+
"return_metadata": false,
|
| 56 |
+
"size": {
|
| 57 |
+
"longest_edge": 25165824,
|
| 58 |
+
"shortest_edge": 4096
|
| 59 |
+
},
|
| 60 |
+
"temporal_patch_size": 2,
|
| 61 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 62 |
+
}
|
| 63 |
+
}
|
run_deploy.log
ADDED
|
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/usr/local/lib/python3.11/site-packages/torch/cuda/__init__.py:65: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
|
| 2 |
+
import pynvml # type: ignore[import]
|
| 3 |
+
(APIServer pid=55824) INFO 07-14 10:50:19 [utils.py:299]
|
| 4 |
+
(APIServer pid=55824) INFO 07-14 10:50:19 [utils.py:299] █ █ █▄ ▄█
|
| 5 |
+
(APIServer pid=55824) INFO 07-14 10:50:19 [utils.py:299] ▄▄ ▄█ █ █ █ ▀▄▀ █ version 0.19.1
|
| 6 |
+
(APIServer pid=55824) INFO 07-14 10:50:19 [utils.py:299] █▄█▀ █ █ █ █ model /workspace/generative-gongyi-generation/grpo/result-1-grpo/20260521/v3-20260521-151950/checkpoint-380-merged
|
| 7 |
+
(APIServer pid=55824) INFO 07-14 10:50:19 [utils.py:299] ▀▀ ▀▀▀▀▀ ▀▀▀▀▀ ▀ ▀
|
| 8 |
+
(APIServer pid=55824) INFO 07-14 10:50:19 [utils.py:299]
|
| 9 |
+
(APIServer pid=55824) INFO 07-14 10:50:19 [utils.py:233] non-default args: {'model_tag': '/workspace/generative-gongyi-generation/grpo/result-1-grpo/20260521/v3-20260521-151950/checkpoint-380-merged', 'chat_template_content_format': 'openai', 'port': 18124, 'model': '/workspace/generative-gongyi-generation/grpo/result-1-grpo/20260521/v3-20260521-151950/checkpoint-380-merged', 'trust_remote_code': True, 'max_model_len': 32768, 'served_model_name': ['adam_a'], 'reasoning_parser': 'qwen3', 'mm_processor_cache_type': 'shm'}
|
| 10 |
+
(APIServer pid=55824) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 11 |
+
(APIServer pid=55824) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 12 |
+
(APIServer pid=55824) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 13 |
+
(APIServer pid=55824) INFO 07-14 10:50:19 [model.py:549] Resolved architecture: Qwen3_5ForConditionalGeneration
|
| 14 |
+
(APIServer pid=55824) INFO 07-14 10:50:19 [model.py:1678] Using max model len 32768
|
| 15 |
+
(APIServer pid=55824) INFO 07-14 10:50:19 [scheduler.py:238] Chunked prefill is enabled with max_num_batched_tokens=8192.
|
| 16 |
+
(APIServer pid=55824) INFO 07-14 10:50:19 [config.py:281] Setting attention block size to 528 tokens to ensure that attention page size is >= mamba page size.
|
| 17 |
+
(APIServer pid=55824) INFO 07-14 10:50:19 [config.py:312] Padding mamba page size by 0.76% to ensure that mamba page size and attention page size are exactly equal.
|
| 18 |
+
(APIServer pid=55824) INFO 07-14 10:50:19 [vllm.py:790] Asynchronous scheduling is enabled.
|
| 19 |
+
(APIServer pid=55824) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 20 |
+
(APIServer pid=55824) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 21 |
+
(APIServer pid=55824) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 22 |
+
(APIServer pid=55824) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 23 |
+
(APIServer pid=55824) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 24 |
+
(APIServer pid=55824) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 25 |
+
/usr/local/lib/python3.11/site-packages/torch/cuda/__init__.py:65: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
|
| 26 |
+
import pynvml # type: ignore[import]
|
| 27 |
+
(EngineCore pid=55905) INFO 07-14 10:50:37 [core.py:105] Initializing a V1 LLM engine (v0.19.1) with config: model='/workspace/generative-gongyi-generation/grpo/result-1-grpo/20260521/v3-20260521-151950/checkpoint-380-merged', speculative_config=None, tokenizer='/workspace/generative-gongyi-generation/grpo/result-1-grpo/20260521/v3-20260521-151950/checkpoint-380-merged', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.bfloat16, max_seq_len=32768, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=False, quantization=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=adam_a, enable_prefix_caching=False, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'cudagraph_mm_encoder': False, 'encoder_cudagraph_token_budgets': [], 'encoder_cudagraph_max_images_per_batch': 0, 'compile_sizes': [], 'compile_ranges_endpoints': [8192], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'size_asserts': False, 'alignment_asserts': False, 'scalar_asserts': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False}, 'max_cudagraph_capture_size': 512, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': True, 'static_all_moe_layers': []}
|
| 28 |
+
(EngineCore pid=55905) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 29 |
+
(EngineCore pid=55905) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 30 |
+
(EngineCore pid=55905) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 31 |
+
(EngineCore pid=55905) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 32 |
+
(EngineCore pid=55905) INFO 07-14 10:50:40 [parallel_state.py:1400] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://10.233.99.253:41813 backend=nccl
|
| 33 |
+
(EngineCore pid=55905) INFO 07-14 10:50:40 [parallel_state.py:1716] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank N/A, EPLB rank N/A
|
| 34 |
+
(EngineCore pid=55905) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 35 |
+
(EngineCore pid=55905) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 36 |
+
(EngineCore pid=55905) INFO 07-14 10:50:48 [gpu_model_runner.py:4735] Starting to load model /workspace/generative-gongyi-generation/grpo/result-1-grpo/20260521/v3-20260521-151950/checkpoint-380-merged...
|
| 37 |
+
(EngineCore pid=55905) INFO 07-14 10:50:49 [cuda.py:390] Using backend AttentionBackendEnum.FLASH_ATTN for vit attention
|
| 38 |
+
(EngineCore pid=55905) INFO 07-14 10:50:49 [mm_encoder_attention.py:230] Using AttentionBackendEnum.FLASH_ATTN for MMEncoderAttention.
|
| 39 |
+
(EngineCore pid=55905) INFO 07-14 10:50:49 [gdn_linear_attn.py:139] Using FlashInfer GDN prefill kernel
|
| 40 |
+
(EngineCore pid=55905) INFO 07-14 10:50:49 [gdn_linear_attn.py:140] FlashInfer GDN prefill kernel is JIT-compiled; first run may take a while to compile. Set `--gdn-prefill-backend triton` to avoid JIT compile time.
|
| 41 |
+
(EngineCore pid=55905) INFO 07-14 10:50:49 [cuda.py:334] Using FLASH_ATTN attention backend out of potential backends: ['FLASH_ATTN', 'FLASHINFER', 'TRITON_ATTN', 'FLEX_ATTENTION'].
|
| 42 |
+
(EngineCore pid=55905) INFO 07-14 10:50:49 [flash_attn.py:596] Using FlashAttention version 3
|
| 43 |
+
(EngineCore pid=55905) <frozen importlib._bootstrap_external>:1241: FutureWarning: The cuda.cudart module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.runtime module instead.
|
| 44 |
+
(EngineCore pid=55905) <frozen importlib._bootstrap_external>:1241: FutureWarning: The cuda.nvrtc module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.nvrtc module instead.
|
| 45 |
+
(EngineCore pid=55905)
|
| 46 |
+
(EngineCore pid=55905)
|
| 47 |
+
(EngineCore pid=55905)
|
| 48 |
+
(EngineCore pid=55905)
|
| 49 |
+
(EngineCore pid=55905)
|
| 50 |
+
(EngineCore pid=55905)
|
| 51 |
+
(EngineCore pid=55905)
|
| 52 |
+
(EngineCore pid=55905) INFO 07-14 10:51:08 [default_loader.py:384] Loading weights took 18.55 seconds
|
| 53 |
+
(EngineCore pid=55905) INFO 07-14 10:51:08 [gpu_model_runner.py:4820] Model loading took 17.66 GiB memory and 19.259625 seconds
|
| 54 |
+
(EngineCore pid=55905) INFO 07-14 10:51:08 [gpu_model_runner.py:5753] Encoder cache will be initialized with a budget of 16384 tokens, and profiled with 1 image items of the maximum feature size.
|
| 55 |
+
(EngineCore pid=55905) INFO 07-14 10:51:17 [backends.py:1051] Using cache directory: /root/.cache/vllm/torch_compile_cache/8118947347/rank_0_0/backbone for vLLM's torch.compile
|
| 56 |
+
(EngineCore pid=55905) INFO 07-14 10:51:17 [backends.py:1111] Dynamo bytecode transform time: 4.98 s
|
| 57 |
+
(EngineCore pid=55905) INFO 07-14 10:51:19 [backends.py:372] Cache the graph of compile range (1, 8192) for later use
|
| 58 |
+
(EngineCore pid=55905) INFO 07-14 10:51:34 [backends.py:390] Compiling a graph for compile range (1, 8192) takes 17.38 s
|
| 59 |
+
(EngineCore pid=55905) INFO 07-14 10:51:36 [decorators.py:655] saved AOT compiled function to /root/.cache/vllm/torch_compile_cache/torch_aot_compile/5fb0cb6e56c12910850a878be8bd3fcdb5d6febcf027f7c4627857b7abf3a61c/rank_0_0/model
|
| 60 |
+
(EngineCore pid=55905) INFO 07-14 10:51:36 [monitor.py:48] torch.compile took 24.73 s in total
|
| 61 |
+
(EngineCore pid=55905) INFO 07-14 10:51:37 [monitor.py:76] Initial profiling/warmup run took 0.86 s
|
| 62 |
+
(EngineCore pid=55905) INFO 07-14 10:51:37 [kv_cache_utils.py:829] Overriding num_gpu_blocks=0 with num_gpu_blocks_override=512
|
| 63 |
+
(EngineCore pid=55905) INFO 07-14 10:51:37 [gpu_model_runner.py:5876] Profiling CUDA graph memory: PIECEWISE=51 (largest=512), FULL=51 (largest=512)
|
| 64 |
+
(EngineCore pid=55905) INFO 07-14 10:51:38 [gpu_model_runner.py:5955] Estimated CUDA graph memory: 0.84 GiB total
|
| 65 |
+
(EngineCore pid=55905) INFO 07-14 10:51:39 [gpu_worker.py:436] Available KV cache memory: 49.49 GiB
|
| 66 |
+
(EngineCore pid=55905) INFO 07-14 10:51:39 [gpu_worker.py:470] In v0.19, CUDA graph memory profiling will be enabled by default (VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=1), which more accurately accounts for CUDA graph memory during KV cache allocation. To try it now, set VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=1 and increase --gpu-memory-utilization from 0.9000 to 0.9107 to maintain the same effective KV cache size.
|
| 67 |
+
(EngineCore pid=55905) INFO 07-14 10:51:39 [kv_cache_utils.py:1319] GPU KV cache size: 404,976 tokens
|
| 68 |
+
(EngineCore pid=55905) INFO 07-14 10:51:39 [kv_cache_utils.py:1324] Maximum concurrency for 32,768 tokens per request: 46.53x
|
| 69 |
+
(EngineCore pid=55905) 2026-07-14 10:51:39,087 - INFO - autotuner.py:262 - flashinfer.jit: [Autotuner]: Autotuning process starts ...
|
| 70 |
+
(EngineCore pid=55905) 2026-07-14 10:51:39,097 - INFO - autotuner.py:268 - flashinfer.jit: [Autotuner]: Autotuning process ends
|
| 71 |
+
(EngineCore pid=55905)
|
| 72 |
+
(EngineCore pid=55905)
|
| 73 |
+
(EngineCore pid=55905) INFO 07-14 10:51:44 [gpu_model_runner.py:6046] Graph capturing finished in 5 secs, took 1.06 GiB
|
| 74 |
+
(EngineCore pid=55905) INFO 07-14 10:51:44 [gpu_worker.py:597] CUDA graph pool memory: 1.06 GiB (actual), 0.84 GiB (estimated), difference: 0.22 GiB (20.7%).
|
| 75 |
+
(EngineCore pid=55905) INFO 07-14 10:51:44 [core.py:283] init engine (profile, create kv cache, warmup model) took 35.36 seconds
|
| 76 |
+
(EngineCore pid=55905) INFO 07-14 10:51:44 [vllm.py:790] Asynchronous scheduling is enabled.
|
| 77 |
+
(APIServer pid=55824) INFO 07-14 10:51:44 [api_server.py:592] Supported tasks: ['generate']
|
| 78 |
+
(APIServer pid=55824) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 79 |
+
(APIServer pid=55824) Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_section', 'mrope_interleaved'}
|
| 80 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [base.py:231] Multi-modal warmup completed in 7.731s
|
| 81 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [api_server.py:596] Starting vLLM server on http://0.0.0.0:18124
|
| 82 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:37] Available routes are:
|
| 83 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /openapi.json, Methods: HEAD, GET
|
| 84 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /docs, Methods: HEAD, GET
|
| 85 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /docs/oauth2-redirect, Methods: HEAD, GET
|
| 86 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /redoc, Methods: HEAD, GET
|
| 87 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /tokenize, Methods: POST
|
| 88 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /detokenize, Methods: POST
|
| 89 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /load, Methods: GET
|
| 90 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /version, Methods: GET
|
| 91 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /health, Methods: GET
|
| 92 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /metrics, Methods: GET
|
| 93 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /v1/models, Methods: GET
|
| 94 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /ping, Methods: GET
|
| 95 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /ping, Methods: POST
|
| 96 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /invocations, Methods: POST
|
| 97 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /v1/chat/completions, Methods: POST
|
| 98 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /v1/chat/completions/batch, Methods: POST
|
| 99 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /v1/responses, Methods: POST
|
| 100 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /v1/responses/{response_id}, Methods: GET
|
| 101 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /v1/responses/{response_id}/cancel, Methods: POST
|
| 102 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /v1/completions, Methods: POST
|
| 103 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /v1/messages, Methods: POST
|
| 104 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /v1/messages/count_tokens, Methods: POST
|
| 105 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /inference/v1/generate, Methods: POST
|
| 106 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /scale_elastic_ep, Methods: POST
|
| 107 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /is_scaling_elastic_ep, Methods: POST
|
| 108 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /v1/chat/completions/render, Methods: POST
|
| 109 |
+
(APIServer pid=55824) INFO 07-14 10:51:55 [launcher.py:46] Route: /v1/completions/render, Methods: POST
|
| 110 |
+
(APIServer pid=55824) INFO: Started server process [55824]
|
| 111 |
+
(APIServer pid=55824) INFO: Waiting for application startup.
|
| 112 |
+
(APIServer pid=55824) INFO: Application startup complete.
|
| 113 |
+
(APIServer pid=55824) ERROR 07-14 11:05:17 [serving.py:193] Error with model error=ErrorInfo(message='The model `adam-a` does not exist.', type='NotFoundError', param='model', code=404)
|
| 114 |
+
(APIServer pid=55824) INFO: 127.0.0.1:58814 - "POST /v1/chat/completions HTTP/1.1" 404 Not Found
|
| 115 |
+
(APIServer pid=55824) INFO: 127.0.0.1:59478 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
| 116 |
+
(APIServer pid=55824) INFO 07-14 11:05:45 [loggers.py:259] Engine 000: Avg prompt throughput: 183.7 tokens/s, Avg generation throughput: 24.5 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 0.0%
|
| 117 |
+
(APIServer pid=55824) INFO 07-14 11:05:55 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 0.0%
|
| 118 |
+
(APIServer pid=55824) INFO 07-14 11:06:35 [loggers.py:259] Engine 000: Avg prompt throughput: 183.5 tokens/s, Avg generation throughput: 80.1 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0%, MM cache hit rate: 50.0%
|
| 119 |
+
(APIServer pid=55824) INFO: 127.0.0.1:47906 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
| 120 |
+
(APIServer pid=55824) INFO 07-14 11:06:45 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 21.3 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 50.0%
|
| 121 |
+
(APIServer pid=55824) INFO 07-14 11:06:55 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 50.0%
|
| 122 |
+
(APIServer pid=55824) INFO: 127.0.0.1:35920 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
| 123 |
+
(APIServer pid=55824) INFO 07-14 11:21:25 [loggers.py:259] Engine 000: Avg prompt throughput: 183.5 tokens/s, Avg generation throughput: 99.1 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
|
| 124 |
+
(APIServer pid=55824) INFO 07-14 11:21:35 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 66.7%
|
| 125 |
+
(APIServer pid=55824) INFO: 127.0.0.1:38174 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
| 126 |
+
(APIServer pid=55824) INFO 07-14 13:04:45 [loggers.py:259] Engine 000: Avg prompt throughput: 183.5 tokens/s, Avg generation throughput: 103.2 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 75.0%
|
| 127 |
+
(APIServer pid=55824) INFO 07-14 13:04:55 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 75.0%
|
| 128 |
+
(APIServer pid=55824) INFO: 127.0.0.1:35282 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
| 129 |
+
(APIServer pid=55824) INFO 07-14 13:09:35 [loggers.py:259] Engine 000: Avg prompt throughput: 1.1 tokens/s, Avg generation throughput: 25.6 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 75.0%
|
| 130 |
+
(APIServer pid=55824) INFO 07-14 13:09:45 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 75.0%
|
| 131 |
+
(APIServer pid=55824) INFO 07-14 13:15:15 [loggers.py:259] Engine 000: Avg prompt throughput: 183.5 tokens/s, Avg generation throughput: 67.3 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0%, MM cache hit rate: 80.0%
|
| 132 |
+
(APIServer pid=55824) INFO: 127.0.0.1:34114 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
| 133 |
+
(APIServer pid=55824) INFO 07-14 13:15:25 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 22.3 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 80.0%
|
| 134 |
+
(APIServer pid=55824) INFO 07-14 13:15:35 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 80.0%
|
| 135 |
+
(APIServer pid=55824) INFO 07-14 13:21:15 [loggers.py:259] Engine 000: Avg prompt throughput: 183.5 tokens/s, Avg generation throughput: 12.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.2%, Prefix cache hit rate: 0.0%, MM cache hit rate: 83.3%
|
| 136 |
+
(APIServer pid=55824) INFO: 127.0.0.1:44944 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
| 137 |
+
(APIServer pid=55824) INFO 07-14 13:21:25 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 82.8 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 83.3%
|
| 138 |
+
(APIServer pid=55824) INFO 07-14 13:21:35 [loggers.py:259] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%, MM cache hit rate: 83.3%
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
|
| 3 |
+
size 19989343
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|endoftext|>",
|
| 24 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 25 |
+
"processor_class": "Qwen3VLProcessor",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "TokenizersBackend",
|
| 28 |
+
"unk_token": null,
|
| 29 |
+
"video_token": "<|video_pad|>",
|
| 30 |
+
"vision_bos_token": "<|vision_start|>",
|
| 31 |
+
"vision_eos_token": "<|vision_end|>"
|
| 32 |
+
}
|