Buckets:
| from dagster import Definitions | |
| from dagster_hf_datasets import HuggingFaceResource | |
| from dagster_hf_datasets.io_manager import HFParquetIOManager | |
| from sanitization_observability.assets import ( | |
| check_no_null_text, | |
| check_retention_rate, | |
| cleaning_quality_report, | |
| deduplicated_fineweb_edu, | |
| filtered_fineweb_edu, | |
| raw_fineweb_edu, | |
| ) | |
| defs = Definitions( | |
| assets=[ | |
| raw_fineweb_edu, | |
| filtered_fineweb_edu, | |
| deduplicated_fineweb_edu, | |
| cleaning_quality_report, | |
| ], | |
| asset_checks=[ | |
| check_no_null_text, | |
| check_retention_rate, | |
| ], | |
| resources={ | |
| "huggingface": HuggingFaceResource( | |
| cache_dir=".hf_cache", | |
| offline=False, | |
| # token="...", # or set HF_TOKEN env var | |
| ), | |
| "hf_parquet_io_manager": HFParquetIOManager( | |
| base_dir=".dagster_hf_storage", | |
| ), | |
| }, | |
| ) | |
Xet Storage Details
- Size:
- 904 Bytes
- Xet hash:
- 3eed28f01ff427aa0cf8a85be80a2608dbfaf0b5cab701062a3af87a65f423f9
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.