| { | |
| "_name_or_path": "lmms-lab/llava-onevision-qwen2-0.5b-ov", | |
| "add_faster_video": false, | |
| "architectures": [ | |
| "EgoGPTQwenForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "delay_load_audio": true, | |
| "eos_token_id": 151645, | |
| "faster_token_stride": 10, | |
| "freeze_mm_mlp_adapter": false, | |
| "freeze_mm_vision_resampler": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 896, | |
| "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, | |
| "image_token_index": 151646, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4864, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 24, | |
| "mm_hidden_size": 1152, | |
| "mm_newline_position": "grid", | |
| "mm_patch_merge_type": "spatial_unpad", | |
| "mm_projector_lr": null, | |
| "mm_projector_type": "mlp2x_gelu", | |
| "mm_resampler_type": null, | |
| "mm_spatial_pool_mode": "bilinear", | |
| "mm_spatial_pool_stride": null, | |
| "mm_speech_encoder_lr": null, | |
| "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model", | |
| "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": "google/siglip-so400m-patch14-384", | |
| "mm_vision_tower_lr": null, | |
| "model_type": "egogpt_qwen", | |
| "num_attention_heads": 14, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "pos_skipping_range": 4096, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "speech_encoder": "./large-v3.pt", | |
| "speech_encoder_ds_rate": 5, | |
| "speech_encoder_hidden_size": 1280, | |
| "speech_encoder_type": "whisper", | |
| "speech_projector_lr": null, | |
| "speech_projector_type": "linear", | |
| "tie_word_embeddings": true, | |
| "tokenizer_model_max_length": 32768, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.45.2", | |
| "tune_mm_mlp_adapter": false, | |
| "unfreeze_mm_speech_encoder": false, | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "use_pos_skipping": false, | |
| "use_sliding_window": false, | |
| "vision_tower_pretrained": "", | |
| "vocab_size": 151936 | |
| } | |