| { |
| "activation_function": "gelu_new", |
| "architectures": [ |
| "LlavaGPTForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_pdrop": 0.1, |
| "bos_token_id": 1, |
| "detect_loss": false, |
| "embd_pdrop": 0.1, |
| "eos_token_id": 2, |
| "freeze_mm_mlp_adapter": false, |
| "hidden_act": "silu", |
| "image_aspect_ratio": "pad", |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "is_decoder": true, |
| "layer_norm_epsilon": 1e-05, |
| "mm_projector_lr": null, |
| "mm_use_im_patch_token": false, |
| "mm_use_im_start_end": false, |
| "mm_vision_tower": "dino", |
| "model_type": "gpt2", |
| "n_embd": 768, |
| "n_head": 12, |
| "n_inner": null, |
| "n_layer": 12, |
| "n_positions": 1024, |
| "num_key_value_heads": 12, |
| "reorder_and_upcast_attn": false, |
| "resid_pdrop": 0.1, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "scale_attn_by_inverse_layer_idx": false, |
| "scale_attn_weights": true, |
| "summary_activation": null, |
| "summary_first_dropout": 0.1, |
| "summary_proj_to_labels": true, |
| "summary_type": "cls_index", |
| "summary_use_proj": true, |
| "tie_word_embeddings": false, |
| "tokenizer_class": "LlamaTokenizer", |
| "tokenizer_model_max_length": 2048, |
| "tokenizer_padding_side": "right", |
| "torch_dtype": "float32", |
| "transformers_version": "4.38.0", |
| "tune_mm_mlp_adapter": false, |
| "use_cache": false, |
| "vision_tower_type": "dino", |
| "vocab_size": 25005 |
| } |
|
|
