config.json

{
  "architectures": [
    "CLIPForImageClassification"
  ],
  "id2label": {
    "0": "extracting_part",
    "1": "no_action",
    "2": "storing_part",
    "3": "unplugging_connector",
    "4": "unscrewing"
  },
  "initializer_factor": 1.0,
  "label2id": {
    "extracting_part": 0,
    "no_action": 1,
    "storing_part": 2,
    "unplugging_connector": 3,
    "unscrewing": 4
  },
  "logit_scale_init_value": 2.6592,
  "model_type": "clip",
  "projection_dim": 512,
  "text_config": {
    "attention_dropout": 0.0,
    "bos_token_id": 0,
    "dropout": 0.0,
    "eos_token_id": 2,
    "hidden_act": "quick_gelu",
    "hidden_size": 512,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 2048,
    "layer_norm_eps": 1e-05,
    "max_position_embeddings": 77,
    "model_type": "clip_text_model",
    "num_attention_heads": 8,
    "num_hidden_layers": 12,
    "projection_dim": 512,
    "torch_dtype": "float32",
    "vocab_size": 49408
  },
  "torch_dtype": "float32",
  "transformers_version": "4.51.3",
  "vision_config": {
    "attention_dropout": 0.0,
    "dropout": 0.0,
    "hidden_act": "quick_gelu",
    "hidden_size": 768,
    "image_size": 224,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "patch_size": 32,
    "projection_dim": 512,
    "torch_dtype": "float32"
  }
}