{ "_name_or_path": "/mnt/bn/tiktok-mm-2/aiic/users/wujinming/code/work_dir/llavanext-Qwen_Qwen1.5-32B-Chat-google_siglip-so400m-patch14-384-pretrain_blip558k_plain-finetune_la1_6mix_lr1e_5_ufvis_lr1e_6_anyres_d32k_fix", "add_faster_video": false, "architectures": [ "LlavaQwenForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "delay_load": false, "eos_token_id": 151645, "freeze_mm_mlp_adapter": false, "freeze_mm_vision_resampler": false, "hidden_act": "silu", "hidden_size": 5120, "image_aspect_ratio": "anyres", "image_crop_resolution": 224, "image_grid_pinpoints": [ [ 384, 768 ], [ 768, 384 ], [ 768, 768 ], [ 1152, 384 ], [ 384, 1152 ] ], "image_split_resolution": 224, "initializer_range": 0.02, "intermediate_size": 27392, "max_position_embeddings": 32768, "max_window_layers": 35, "mm_hidden_size": 1152, "mm_newline_position": "grid", "mm_patch_merge_type": "spatial_unpad", "mm_pooling_position": "after", "mm_projector_lr": null, "mm_projector_type": "mlp2x_gelu", "mm_resampler_type": null, "mm_spatial_pool_mode": "average", "mm_spatial_pool_stride": 2, "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, "modality_max_length": "None", "model_type": "llava", "num_attention_heads": 40, "num_hidden_layers": 64, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": false, "tokenizer_model_max_length": 32768, "tokenizer_padding_side": "right", "torch_dtype": "bfloat16", "transformers_version": "4.39.2", "tune_mm_mlp_adapter": false, "tune_mm_vision_resampler": false, "unfreeze_mm_vision_tower": false, "use_cache": true, "use_mm_proj": true, "use_sliding_window": false, "vision_tower_pretrained": null, "vocab_size": 152064, "text_config": { "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 27392, "max_position_embeddings": 32768, "max_window_layers": 35, "model_type": "qwen2", "num_attention_heads": 40, "num_hidden_layers": 64, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.37.2", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064 } }