| { |
| "_name_or_path": "/workspace/checkpoints/vlora-qwen2.5-3B-sft-sum-bs256/", |
| "architectures": [ |
| "LlavaQwen2VLoRAForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "eos_token_id": 151645, |
| "freeze_mm_mlp_adapter": false, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "image_aspect_ratio": "anyres_max_9", |
| "image_crop_resolution": null, |
| "image_grid_pinpoints": [ |
| [ |
| 384, |
| 384 |
| ], |
| [ |
| 384, |
| 768 |
| ], |
| [ |
| 384, |
| 1152 |
| ], |
| [ |
| 384, |
| 1536 |
| ], |
| [ |
| 384, |
| 1920 |
| ], |
| [ |
| 384, |
| 2304 |
| ], |
| [ |
| 768, |
| 384 |
| ], |
| [ |
| 768, |
| 768 |
| ], |
| [ |
| 768, |
| 1152 |
| ], |
| [ |
| 768, |
| 1536 |
| ], |
| [ |
| 768, |
| 1920 |
| ], |
| [ |
| 768, |
| 2304 |
| ], |
| [ |
| 1152, |
| 384 |
| ], |
| [ |
| 1152, |
| 768 |
| ], |
| [ |
| 1152, |
| 1152 |
| ], |
| [ |
| 1152, |
| 1536 |
| ], |
| [ |
| 1152, |
| 1920 |
| ], |
| [ |
| 1152, |
| 2304 |
| ], |
| [ |
| 1536, |
| 384 |
| ], |
| [ |
| 1536, |
| 768 |
| ], |
| [ |
| 1536, |
| 1152 |
| ], |
| [ |
| 1536, |
| 1536 |
| ], |
| [ |
| 1536, |
| 1920 |
| ], |
| [ |
| 1536, |
| 2304 |
| ], |
| [ |
| 1920, |
| 384 |
| ], |
| [ |
| 1920, |
| 768 |
| ], |
| [ |
| 1920, |
| 1152 |
| ], |
| [ |
| 1920, |
| 1536 |
| ], |
| [ |
| 1920, |
| 1920 |
| ], |
| [ |
| 1920, |
| 2304 |
| ], |
| [ |
| 2304, |
| 384 |
| ], |
| [ |
| 2304, |
| 768 |
| ], |
| [ |
| 2304, |
| 1152 |
| ], |
| [ |
| 2304, |
| 1536 |
| ], |
| [ |
| 2304, |
| 1920 |
| ], |
| [ |
| 2304, |
| 2304 |
| ] |
| ], |
| "image_split_resolution": null, |
| "initializer_range": 0.02, |
| "intermediate_size": 11008, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 70, |
| "mm_hidden_size": 1152, |
| "mm_projector_lr": null, |
| "mm_projector_type": "vlora", |
| "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": "/workspace/models/siglip-so400m-patch14-384", |
| "model_type": "llava_qwen_vlora", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 36, |
| "num_key_value_heads": 2, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000.0, |
| "skip_layers": 4, |
| "sliding_window": 32768, |
| "tie_word_embeddings": true, |
| "tokenizer_model_max_length": 4096, |
| "tokenizer_padding_side": "right", |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.37.2", |
| "tune_mm_mlp_adapter": false, |
| "tune_vision_tower": true, |
| "use_cache": true, |
| "use_mm_proj": true, |
| "use_sliding_window": false, |
| "vision_tower_lr": 2e-06, |
| "vlora_alpha": 64, |
| "vlora_depth": 8, |
| "vlora_dim": 512, |
| "vlora_groups": 8, |
| "vlora_llm_depth": 36, |
| "vlora_llm_dim": 2048, |
| "vlora_pos_num": 729, |
| "vlora_rank": 64, |
| "vlora_type": "qkvom", |
| "vlora_type_group": "kv", |
| "vlora_visual_dim": 1152, |
| "vocab_size": 151936, |
| "weights_sep": true |
| } |
|
|