{ "_name_or_path": "/tmp/iopath_cache/manifold_cache/tree/users/shenx/finetune/10162317-cambrian_llama3_2-1b_t576_ov", "architectures": [ "CambrianLlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "connect_layer": 2, "connector_depth": 3, "connector_only": true, "dino_threshold": 0.83, "drop_threshold": 0.8, "eos_token_id": [ 128001, 128008, 128009 ], "frame_pos": false, "freeze_mm_mlp_adapter": false, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "highres": true, "highres_connect": false, "image_aspect_ratio": "pad", "image_position": 91, "image_token_len": 576, "initializer_range": 0.02, "intermediate_size": 8192, "is_image_newline": true, "is_st_sampler": false, "lowres_token": 8, "max_position_embeddings": 131072, "mlp_bias": false, "mm_patch_merge_type": "flat", "mm_projector_lr": null, "mm_projector_type": "sva", "mm_use_im_patch_token": false, "mm_use_im_start_end": false, "mm_vision_sampler_lr": null, "mm_vision_select_feature": "patch", "mm_vision_select_layer": -2, "mm_vision_tower_aux_list": [ "siglip/CLIP-ViT-SO400M-14-384", "facebook/dinov2-giant-res378" ], "mm_vision_tower_aux_token_len_list": [ 576, 576 ], "mm_vision_tower_lr": null, "model_type": "cambrian_llama", "num_attention_heads": 32, "num_hidden_layers": 16, "num_key_value_heads": 8, "num_of_vision_sampler_layers": 10, "num_query_group": 1, "pretraining_tp": 1, "query_num_list": [ 576 ], "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 32.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000.0, "spmd_debug": null, "spmd_fsdp_sharding": null, "spmd_mesh": null, "start_of_vision_sampler_layers": 0, "stride_of_vision_sampler_layers": 3, "tie_word_embeddings": false, "tokenizer_model_max_length": 16000, "tokenizer_padding_side": "right", "torch_dtype": "float32", "transformers_version": "4.44.2", "tune_mm_mlp_adapter": false, "unfreeze_mm_vision_tower": false, "use_cache": false, "use_mm_proj": true, "vision_hidden_size": 1024, "vision_tower_aux_token_len_list": [ 576, 576 ], "vocab_size": 128256 }