{
  "_name_or_path": "openai/clip-vit-base-patch16",
  "architectures": [
    "CLIPForImageClassification"
  ],
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4",
    "5": "LABEL_5",
    "6": "LABEL_6",
    "7": "LABEL_7"
  },
  "initializer_factor": 1.0,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2,
    "LABEL_3": 3,
    "LABEL_4": 4,
    "LABEL_5": 5,
    "LABEL_6": 6,
    "LABEL_7": 7
  },
  "logit_scale_init_value": 2.6592,
  "model_type": "clip",
  "problem_type": "single_label_classification",
  "projection_dim": 512,
  "text_config": {
    "bos_token_id": 0,
    "dropout": 0.0,
    "eos_token_id": 2,
    "model_type": "clip_text_model"
  },
  "torch_dtype": "float32",
  "transformers_version": "4.45.2",
  "vision_config": {
    "dropout": 0.0,
    "model_type": "clip_vision_model",
    "patch_size": 16
  }
}