config.json
| 1 | { |
| 2 | "architectures": [ |
| 3 | "SiglipForImageClassification" |
| 4 | ], |
| 5 | "id2label": { |
| 6 | "0": "Female \u2640", |
| 7 | "1": "Male \u2642" |
| 8 | }, |
| 9 | "initializer_factor": 1.0, |
| 10 | "label2id": { |
| 11 | "Female \u2640": 0, |
| 12 | "Male \u2642": 1 |
| 13 | }, |
| 14 | "model_type": "siglip", |
| 15 | "problem_type": "single_label_classification", |
| 16 | "text_config": { |
| 17 | "attention_dropout": 0.0, |
| 18 | "hidden_act": "gelu_pytorch_tanh", |
| 19 | "hidden_size": 768, |
| 20 | "intermediate_size": 3072, |
| 21 | "layer_norm_eps": 1e-06, |
| 22 | "max_position_embeddings": 64, |
| 23 | "model_type": "siglip_text_model", |
| 24 | "num_attention_heads": 12, |
| 25 | "num_hidden_layers": 12, |
| 26 | "projection_size": 768, |
| 27 | "torch_dtype": "float32", |
| 28 | "vocab_size": 256000 |
| 29 | }, |
| 30 | "torch_dtype": "float32", |
| 31 | "transformers_version": "4.51.0.dev0", |
| 32 | "vision_config": { |
| 33 | "attention_dropout": 0.0, |
| 34 | "hidden_act": "gelu_pytorch_tanh", |
| 35 | "hidden_size": 768, |
| 36 | "image_size": 224, |
| 37 | "intermediate_size": 3072, |
| 38 | "layer_norm_eps": 1e-06, |
| 39 | "model_type": "siglip_vision_model", |
| 40 | "num_attention_heads": 12, |
| 41 | "num_channels": 3, |
| 42 | "num_hidden_layers": 12, |
| 43 | "patch_size": 16, |
| 44 | "torch_dtype": "float32" |
| 45 | } |
| 46 | } |
| 47 | |