config.json

{
  "export_model_type": "clip",
  "initializer_factor": 1.0,
  "logit_scale_init_value": 2.6592,
  "model_cfg": {
    "embed_dim": 8,
    "text_cfg": {
      "context_length": 77,
      "heads": 2,
      "layers": 2,
      "vocab_size": 49408,
      "width": 8
    },
    "vision_cfg": {
      "image_size": 8,
      "layers": 2,
      "patch_size": 2,
      "width": 128
    }
  },
  "model_type": "clip",
  "preprocess_cfg": {
    "mean": [
      0.5,
      0.5,
      0.5
    ],
    "std": [
      0.5,
      0.5,
      0.5
    ]
  },
  "projection_dim": 512,
  "text_config": {
    "context_length": 77,
    "heads": 2,
    "layers": 2,
    "model_type": "clip_text_model",
    "width": 8
  },
  "transformers_version": "4.41.2",
  "vision_config": {
    "image_size": 8,
    "layers": 2,
    "model_type": "clip_vision_model",
    "patch_size": 2,
    "width": 128
  }
}