open_clip_config.json

{
  "model_cfg": {
    "embed_dim": 768,
    "vision_cfg": {
      "image_size": 224,
      "layers": 24,
      "width": 1024,
      "patch_size": 14,
      "output_tokens": true,
      "pool_type": "avg_all",
      "final_ln_after_pool": true
    },
    "text_cfg": {
      "context_length": 77,
      "vocab_size": 49408,
      "width": 768,
      "heads": 12,
      "layers": 12,
      "output_tokens": true,
      "cross_attn_ratio": 2,
      "does_full_decoding": true
    },
    "custom_text": true
  },
  "preprocess_cfg": {
    "mean": [
      0.48145466,
      0.4578275,
      0.40821073
    ],
    "std": [
      0.26862954,
      0.26130258,
      0.27577711
    ],
    "interpolation": "bicubic",
    "resize_mode": "shortest"
  }
}