{ "_name_or_path": "/mnt/bn/tiktok-mm-3/aiic/users/chenjoya/projects/pretraining/maas_engine/cache/onevision-qwen2-siglip-7b_pt-60x1fps-interval1silence-title+asr-31.52m-60s-word-youtube_1113/model/output/", "architectures": [ "LlavaQwenForCausalLM" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_llavaqwen.LlavaQwenConfig", "AutoModel": "modeling_llavaqwen.LlavaQwenForCausalLM" }, "bos_token_id": 151643, "delay_load": false, "eos_token_id": 151645, "freeze_mm_frame_selector": false, "hidden_act": "silu", "hidden_size": 3584, "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": 18944, "max_position_embeddings": 32768, "max_window_layers": 28, "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": "spatial_pool", "mm_smarter_frames_feat_enhance": "original", "mm_smarter_frames_sel_num": 32, "mm_smarter_frames_sel_position": "before", "mm_smarter_frames_sel_strategy": "all", "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": 2e-06, "model_type": "llava_qwen", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "pos_skipping_range": 4096, "pretrain_mm_frame_selector": "none", "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "save_model_id": "onevision-qwen2-siglip-7b_pt-60x1fps-interval1silence-title+asr-31.52m-60s-word-youtube_1113", "sliding_window": 131072, "tie_word_embeddings": false, "tokenizer_model_max_length": 32768, "tokenizer_padding_side": "right", "torch_dtype": "bfloat16", "transformers_version": "4.40.0.dev0", "tune_mm_frame_selector": false, "use_cache": false, "use_mm_proj": true, "use_pos_skipping": false, "use_sliding_window": false, "vision_tower_pretrained": null, "vocab_size": 152064 }