{ "_name_or_path": "/weka/oe-training-default/jamesp/code/Osprey/exp/osprey_multi_region_instruct_v1_cot_text_sharegpt_flickr_osprey_stage3-stage3-qwen2.5-3b-instruct-lr1e-5-unfreeze_mm_vision_tower_bs128_epoch2_v4", "architectures": [ "RobinQwenForCausalLM" ], "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": "pad", "image_crop_resolution": null, "image_grid_pinpoints": null, "image_split_resolution": null, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 32768, "max_window_layers": 70, "mm_projector_type": "mlp2x_gelu", "mm_use_im_patch_token": false, "mm_use_im_start_end": false, "mm_vision_tower": "/net/nfs3.prior/jamesp/models/CLIP-convnext_large_d_320.laion2B-s29B-b131K-ft-soup/open_clip_pytorch_model.bin", "mm_vision_tower_lr": 2e-06, "model_type": "robin_qwen", "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, "sliding_window": null, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.43.3", "tune_mm_mlp_adapter": false, "unfreeze_mm_vision_tower": true, "use_cache": true, "use_mm_proj": true, "use_sliding_window": false, "vocab_size": 151936 }