| { |
| "_name_or_path": "liuhaotian/llava-v1.5-7b", |
| "architectures": [ |
| "LlavaLlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "freeze_mm_mlp_adapter": false, |
| "freeze_mm_vision_resampler": false, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "image_aspect_ratio": "pad", |
| "initializer_range": 0.02, |
| "intermediate_size": 11008, |
| "link_token_indices": -1000000, |
| "max_length": 4096, |
| "max_position_embeddings": 4096, |
| "mm_hidden_size": 1024, |
| "mm_inst_prompt_encoder": "shared_projector", |
| "mm_patch_merge_type": "flat", |
| "mm_pointcloud_tower": "./checkpoints/pc_pretrained/ost-sa-only-llava-align-scannet200.pth", |
| "mm_projector_lr": null, |
| "mm_projector_type": "mlp2x_gelu", |
| "mm_resampler_type": null, |
| "mm_use_im_patch_token": false, |
| "mm_use_im_start_end": false, |
| "mm_vision_select_feature": "patch", |
| "mm_vision_select_layer": -1, |
| "mm_vision_tower": null, |
| "model_type": "llava_llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 32, |
| "num_pc_tokens": 100, |
| "pad_token_id": 0, |
| "pc_feature_dim": 1024, |
| "pc_hidden_size": 1024, |
| "pc_projector_lr": null, |
| "pc_sampling_type": "superpoint", |
| "pointcloud_decoder_lr": null, |
| "pointcloud_tower_lr": null, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "seg_token_idx": 32000, |
| "tie_word_embeddings": false, |
| "tokenizer_model_max_length": 4096, |
| "tokenizer_padding_side": "right", |
| "torch_dtype": "float16", |
| "transformers_version": "4.37.2", |
| "tune_mm_mlp_adapter": false, |
| "tune_mm_vision_resampler": false, |
| "unfreeze_mm_vision_tower": false, |
| "use_cache": true, |
| "use_mm_proj": true, |
| "use_pc_proj": true, |
| "vocab_size": 32001 |
| } |
|
|
