| { | |
| "_name_or_path": "./checkpoints/ShareGPT4V-13B_Pretrained_vit-large336-l12_vicuna-13b-v1.5", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "freeze_mm_mlp_adapter": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "image_aspect_ratio": "pad", | |
| "image_grid_pinpoints": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "loss_alpha": 0.5, | |
| "max_position_embeddings": 2048, | |
| "mm_hidden_size": 1024, | |
| "mm_projector_lr": 2e-05, | |
| "mm_projector_type": "cluster", | |
| "mm_use_im_patch_token": false, | |
| "mm_use_im_start_end": false, | |
| "mm_vision_select_feature": "patch", | |
| "mm_vision_select_layer": -2, | |
| "mm_vision_tower": "Lin-Chen/ShareGPT4V-13B_Pretrained_vit-large336-l12", | |
| "model_type": "llama", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 40, | |
| "num_latents": 256, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "qav_loss": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.31.0", | |
| "tune_mm_mlp_adapter": false, | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "vision_tower_lr": 0.0002, | |
| "vocab_size": 32000 | |
| } | |