| { | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "output_attentions": false, | |
| "torchscript": false, | |
| "torch_dtype": null, | |
| "use_bfloat16": false, | |
| "tf_legacy_loss": false, | |
| "pruned_heads": {}, | |
| "tie_word_embeddings": true, | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "is_decoder": true, | |
| "cross_attention_hidden_size": null, | |
| "add_cross_attention": false, | |
| "tie_encoder_decoder": false, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "num_beams": 1, | |
| "num_beam_groups": 1, | |
| "diversity_penalty": 0.0, | |
| "temperature": 1.0, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "typical_p": 1.0, | |
| "repetition_penalty": 1.0, | |
| "length_penalty": 1.0, | |
| "no_repeat_ngram_size": 0, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "bad_words_ids": null, | |
| "num_return_sequences": 1, | |
| "output_scores": false, | |
| "return_dict_in_generate": false, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "remove_invalid_values": false, | |
| "exponential_decay_length_penalty": null, | |
| "suppress_tokens": null, | |
| "begin_suppress_tokens": null, | |
| "architectures": [ | |
| "TinyLLM" | |
| ], | |
| "finetuning_task": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "tokenizer_class": null, | |
| "prefix": null, | |
| "bos_token_id": 1, | |
| "pad_token_id": 73440, | |
| "eos_token_id": 73440, | |
| "sep_token_id": null, | |
| "decoder_start_token_id": null, | |
| "task_specific_params": null, | |
| "problem_type": null, | |
| "_name_or_path": "", | |
| "_commit_hash": null, | |
| "_attn_implementation_internal": null, | |
| "_attn_implementation_autoset": false, | |
| "transformers_version": null, | |
| "vision_use_rmsnorm": true, | |
| "qformer_num_layers": 4, | |
| "qformer_mlp_ratio": 2.0, | |
| "vocab_size": 73448, | |
| "hidden_size": 1280, | |
| "num_hidden_layers": 24, | |
| "num_attention_heads": 20, | |
| "num_key_value_heads": 4, | |
| "max_position_embeddings": 8192, | |
| "RoPE_base": 10000.0, | |
| "rope_type": "yarn", | |
| "dropout": 0.0, | |
| "train_maxlength": 8192, | |
| "rms_norm_eps": 1e-05, | |
| "qkrms_norm_eps": 1e-05, | |
| "use_qk_norm": true, | |
| "kv_cache_dtype": "auto", | |
| "use_moe": false, | |
| "adapter_type": "none", | |
| "use_ssm": false, | |
| "ssm_layers": [], | |
| "embeddingdropout": 0.0, | |
| "learnable_temp": true, | |
| "use_affine": true, | |
| "use_sampleatt": false, | |
| "use_swiGLU": true, | |
| "mlp_ratio": 4.5, | |
| "ignore_index": -100, | |
| "loss_reduction": "hybrid", | |
| "sample_mean_alpha": 0.75, | |
| "drop_path": 0.0, | |
| "residual_dropout": 0.0, | |
| "moe_layers": [], | |
| "num_expert": 4, | |
| "moe_use_detach": false, | |
| "moe_cap_factor": 1.5, | |
| "moe_aux_weight": 5.0, | |
| "use_checkpoint": false, | |
| "checkpoint_use_reentrant": false, | |
| "use_adaptive_softmax": true, | |
| "adaptive_cutoffs": [ | |
| 20000, | |
| 60000 | |
| ], | |
| "adaptive_div": 4.0, | |
| "adaptive_calibrate_every": 200, | |
| "use_tcn": false, | |
| "tcn_layers": [], | |
| "drop_high_loss": 0.0, | |
| "mlp_ratio_front": 3.5, | |
| "mlp_ratio_mid": 4.0, | |
| "mlp_ratio_back": 4.5, | |
| "mlp_mid_start": 8, | |
| "mlp_back_start": 16, | |
| "mlp_ratio_overrides": { | |
| "21": 5.0, | |
| "22": 5.0, | |
| "23": 5.0 | |
| }, | |
| "eso_loss_radio": 1.0, | |
| "use_vision": true, | |
| "vision_feature_dim": 1024, | |
| "max_vision_tokens": 0, | |
| "vision_mlp_ratio": 4.0, | |
| "vision_use_swiglu": true, | |
| "vision_dropout": 0.0, | |
| "num_query_tokens": 128, | |
| "auto_map": { | |
| "AutoConfig": "configuration_tinyllm.Config", | |
| "AutoModelForCausalLM": "modeling_tinyllm.TinyLLM" | |
| }, | |
| "vision_tower_name_or_path": "OpenGVLab/InternViT-300M-448px-V2_5" | |
| } | |