open_clip_config.json

{
  "model_cfg": {
    "embed_dim": 768,
    "vision_cfg": {
      "image_size": 336,
      "layers": 24,
      "width": 1024,
      "patch_size": 14,
      "no_ln_pre": true,
      "pool_type": "avg",
      "final_ln_after_pool": true
    },
    "text_cfg": {
      "context_length": 80,
      "vocab_size": 32000,
      "hf_tokenizer_name": "bert-base-uncased",
      "tokenizer_kwargs": {
        "strip_sep_token": true
      },
      "width": 768,
      "heads": 12,
      "layers": 12,
      "pool_type": "last",
      "no_causal_mask": true,
      "act_kwargs": {
        "approximate": "tanh"
      }
    }
  },
  "preprocess_cfg": {
    "mean": [
      0.485,
      0.456,
      0.406
    ],
    "std": [
      0.229,
      0.224,
      0.225
    ],
    "interpolation": "bilinear",
    "resize_mode": "squash"
  }
}