| { | |
| "architectures": [ | |
| "SiglipModel" | |
| ], | |
| "initializer_factor": 1.0, | |
| "model_type": "siglip", | |
| "text_config": { | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "model_type": "siglip_text_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.37.0.dev0", | |
| "vision_config": { | |
| "hidden_size": 1152, | |
| "image_size": 448, | |
| "intermediate_size": 4304, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27, | |
| "num_image_tokens": 256, | |
| "patch_size": 14, | |
| "projection_dim": 2048, | |
| "projector_hidden_act": "gelu_fast", | |
| "vision_use_head": false | |
| } | |
| } | |