{ "mic": "0.3", "name": "VideoMAE pretraining", "usage": "VideoMAEImageProcessor + VideoMAEForPreTraining, synthetic videos, masked patch reconstruction", "architecture": "VideoMAEForPreTraining", "checkpoints": { "MCG-NJU/videomae-base": { "fixture": "huggingface-mic/videomae-base-mic" } }, "fixtures": { "huggingface-mic/videomae-base-mic": { "built_from": "MCG-NJU/videomae-base", "covers": [ "MCG-NJU/videomae-base" ], "build": { "seed": 17, "model_class": "VideoMAEForPreTraining" } } }, "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": { "download_mb": 20 }, "MCG-NJU/videomae-base": { "memory_gb": 4, "download_mb": 400 } } } }, "outputs": { "runtime": { "compare": "exact" }, "logits.probe": { "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" } } }