{
  "architectures": ["SigLIP"],
  "auto_map": {
    "AutoConfig": "marqo_fashionSigLIP.MarqoFashionSigLIPConfig",
    "AutoModel": "marqo_fashionSigLIP.MarqoFashionSigLIP",
    "AutoProcessor": "marqo_fashionSigLIP.MarqoFashionSigLIPProcessor"
  },
  "open_clip_model_name": "hf-hub:pySilver/marqo-fashionSigLIP-ST",
  "model_type": "siglip",
  "hidden_size": 768,
  "projection_dim": 768,
  "text_config": {
    "attention_dropout": 0.0,
    "bos_token_id": 49406,
    "eos_token_id": 49407,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-6,
    "max_position_embeddings": 64,
    "model_type": "siglip_text_model",
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "pad_token_id": 1,
    "transformers_version": "4.47.1",
    "vocab_size": 32000
  },
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "image_size": 224,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-6,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "patch_size": 16,
    "transformers_version": "4.47.1"
  },
  "initializer_factor": 1.0,
  "return_dict": true,
  "output_hidden_states": false,
  "output_attentions": false,
  "torchscript": false,
  "use_bfloat16": false,
  "tie_word_embeddings": true
}