| { | |
| "architectures": [ | |
| "LlavaLlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128009, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "image_aspect_ratio": "pad", | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "mm_hidden_size": 1024, | |
| "mm_patch_merge_type": "flat", | |
| "mm_projector": { | |
| "hidden_size": 4096, | |
| "mlp_depth": 2, | |
| "mm_hidden_size": 1024, | |
| "type": "MLPProjector" | |
| }, | |
| "mm_projector_lr": null, | |
| "mm_use_im_patch_token": false, | |
| "mm_use_im_start_end": false, | |
| "mm_vision_tower": { | |
| "mm_vision_select_feature": "patch", | |
| "mm_vision_select_layer": -2, | |
| "pretrained_model_name_or_path": "/cache/data/huggingface_models/clip-vit-large-patch14-336", | |
| "type": "CLIPVisionTower" | |
| }, | |
| "model_type": "llava_llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": false, | |
| "tokenizer_model_max_length": 4096, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.46.2", | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "vocab_size": 128257 | |
| } | |