{
  "_name_or_path": "openai/clip-vit-large-patch14",
  "architectures": [
    "CLIPForImageClassification"
  ],
  "id2label": {
    "0": "T - shirt / top",
    "1": "Trouser",
    "2": "Pullover",
    "3": "Dress",
    "4": "Coat",
    "5": "Sandal",
    "6": "Shirt",
    "7": "Sneaker",
    "8": "Bag",
    "9": "Ankle boot"
  },
  "initializer_factor": 1.0,
  "label2id": {
    "Ankle boot": "9",
    "Bag": "8",
    "Coat": "4",
    "Dress": "3",
    "Pullover": "2",
    "Sandal": "5",
    "Shirt": "6",
    "Sneaker": "7",
    "T - shirt / top": "0",
    "Trouser": "1"
  },
  "logit_scale_init_value": 2.6592,
  "model_type": "clip",
  "problem_type": "single_label_classification",
  "projection_dim": 768,
  "text_config": {
    "dropout": 0.0,
    "hidden_size": 768,
    "intermediate_size": 3072,
    "model_type": "clip_text_model",
    "num_attention_heads": 12,
    "projection_dim": 768
  },
  "torch_dtype": "float32",
  "transformers_version": "4.40.1",
  "vision_config": {
    "dropout": 0.0,
    "hidden_size": 1024,
    "intermediate_size": 4096,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768
  }
}