{ "_name_or_path": "/model/experiments/0050_vila_step2/checkpoints/llm-jp-3-13b-instruct_siglip_mlp2xgelu_step-2_lr_1e-5_20241011/vision_tower", "architectures": [ "SiglipVisionModel" ], "attention_dropout": 0.0, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "image_size": 384, "intermediate_size": 4304, "layer_norm_eps": 1e-06, "model_type": "siglip_vision_model", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 27, "patch_size": 14, "torch_dtype": "bfloat16", "transformers_version": "4.36.2" }