config.json

{
  "architectures": [
    "SiglipForImageClassification"
  ],
  "id2label": {
    "0": "calling",
    "1": "clapping",
    "2": "cycling",
    "3": "dancing",
    "4": "drinking",
    "5": "eating",
    "6": "fighting",
    "7": "hugging",
    "8": "laughing",
    "9": "listening_to_music",
    "10": "running",
    "11": "sitting",
    "12": "sleeping",
    "13": "texting",
    "14": "using_laptop"
  },
  "initializer_factor": 1.0,
  "label2id": {
    "calling": 0,
    "clapping": 1,
    "cycling": 2,
    "dancing": 3,
    "drinking": 4,
    "eating": 5,
    "fighting": 6,
    "hugging": 7,
    "laughing": 8,
    "listening_to_music": 9,
    "running": 10,
    "sitting": 11,
    "sleeping": 12,
    "texting": 13,
    "using_laptop": 14
  },
  "model_type": "siglip",
  "problem_type": "single_label_classification",
  "text_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-06,
    "max_position_embeddings": 64,
    "model_type": "siglip_text_model",
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "projection_size": 768,
    "torch_dtype": "float32",
    "vocab_size": 256000
  },
  "torch_dtype": "float32",
  "transformers_version": "4.50.3",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "image_size": 224,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "patch_size": 16,
    "torch_dtype": "float32"
  }
}