{
  "mic": "0.3",
  "name": "CLIP vision embedding",
  "usage": "CLIPImageProcessor + CLIPVisionModelWithProjection, two synthetic images, batched, image_embeds probe, one SGD step on the projection head",
  "architecture": "CLIPVisionModelWithProjection",
  "checkpoints": {
    "kunalkanaujiya/clip-vit-base-patch32-vision": {
      "fixture": "huggingface-mic/clip-vit-base-patch32-vision-mic"
    }
  },
  "fixtures": {
    "huggingface-mic/clip-vit-base-patch32-vision-mic": {
      "built_from": "kunalkanaujiya/clip-vit-base-patch32-vision",
      "covers": [
        "kunalkanaujiya/clip-vit-base-patch32-vision"
      ],
      "build": {
        "seed": 17,
        "model_class": "CLIPVisionModelWithProjection"
      }
    }
  },
  "integrations": {
    "transformers": {
      "entry_point": "integrations/transformers/usage.md",
      "format": "runnable-markdown",
      "requires": [
        "transformers>=5",
        "torch"
      ],
      "targets": [
        "fixtures",
        "checkpoints"
      ],
      "variants": {
        "default": {},
        "eager": {
          "attn_implementation": "eager"
        },
        "bfloat16": {
          "dtype": "bfloat16"
        }
      },
      "training": true,
      "resources": {
        "fixture": {
          "memory_gb": 2,
          "download_mb": 20
        },
        "kunalkanaujiya/clip-vit-base-patch32-vision": {
          "memory_gb": 3,
          "download_mb": 350
        }
      }
    }
  },
  "outputs": {
    "runtime": {
      "compare": "exact"
    },
    "image_embeds": {
      "compare": "allclose",
      "atol": 0.0001,
      "rtol": 0.0001
    },
    "embedding_norms": {
      "compare": "allclose",
      "atol": 0.0001,
      "rtol": 0.0001
    },
    "training.loss": {
      "compare": "allclose",
      "atol": 0.0001,
      "rtol": 0.0001
    },
    "training.gradients": {
      "compare": "all_true"
    },
    "training.updated": {
      "compare": "true"
    }
  }
}