{ "mic": "0.3", "name": "BigBird pretraining (MLM + NSP)", "usage": "AutoTokenizer + AutoModelForPreTraining, batched with right padding, block-sparse attention", "architecture": "BigBirdForPreTraining", "checkpoints": { "google/bigbird-roberta-base": { "fixture": "huggingface-mic/bigbird-roberta-base-mic" } }, "fixtures": { "huggingface-mic/bigbird-roberta-base-mic": { "built_from": "google/bigbird-roberta-base", "covers": [ "google/bigbird-roberta-base" ], "build": { "seed": 17, "model_class": "BigBirdForPreTraining" } } }, "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, "gpu_memory_gb": 4 }, "google/bigbird-roberta-base": { "memory_gb": 8, "gpu_memory_gb": 8, "download_mb": 500 } } } }, "outputs": { "runtime": { "compare": "exact" }, "prediction_logits": { "compare": "allclose", "atol": 0.0001, "rtol": 0.0001 }, "seq_relationship_logits": { "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" } } }