| { | |
| "mic": "0.3", | |
| "name": "CLIP zero-shot image classification", | |
| "usage": "CLIPProcessor + CLIPModel, image-caption matching, batched", | |
| "architecture": "CLIPModel", | |
| "checkpoints": { | |
| "openai/clip-vit-base-patch32": { | |
| "fixture": "hf-internal-testing/mic-clip-slim" | |
| } | |
| }, | |
| "fixtures": { | |
| "hf-internal-testing/mic-clip-slim": { | |
| "built_from": "openai/clip-vit-base-patch32", | |
| "covers": [ | |
| "openai/clip-vit-base-patch32" | |
| ], | |
| "build": { | |
| "seed": 17 | |
| } | |
| } | |
| }, | |
| "integrations": { | |
| "transformers": { | |
| "entry_point": "integrations/transformers/usage.md", | |
| "format": "runnable-markdown", | |
| "requires": [ | |
| "transformers>=5", | |
| "torch", | |
| "Pillow" | |
| ], | |
| "targets": [ | |
| "fixtures" | |
| ], | |
| "variants": { | |
| "default": {}, | |
| "eager": { | |
| "attn_implementation": "eager" | |
| }, | |
| "bfloat16": { | |
| "dtype": "bfloat16" | |
| } | |
| }, | |
| "training": true, | |
| "resources": { | |
| "fixture": { | |
| "memory_gb": 1, | |
| "download_mb": 20 | |
| }, | |
| "openai/clip-vit-base-patch32": { | |
| "memory_gb": 2, | |
| "download_mb": 605 | |
| } | |
| } | |
| } | |
| }, | |
| "outputs": { | |
| "runtime": { | |
| "compare": "exact" | |
| }, | |
| "image_to_text": { | |
| "compare": "exact" | |
| }, | |
| "text_to_image": { | |
| "compare": "exact" | |
| }, | |
| "logits_per_image": { | |
| "compare": "allclose", | |
| "atol": 0.0001, | |
| "rtol": 0.0001 | |
| }, | |
| "text_kwargs_input_ids": { | |
| "compare": "exact" | |
| }, | |
| "image_processor_config_keys": { | |
| "compare": "exact" | |
| }, | |
| "training.loss": { | |
| "compare": "allclose", | |
| "atol": 0.0001, | |
| "rtol": 0.0001 | |
| }, | |
| "training.gradients": { | |
| "compare": "all_true" | |
| }, | |
| "training.updated": { | |
| "compare": "true" | |
| } | |
| } | |
| } | |