metadata
license: apache-2.0
datasets:
- DeltonLabs/DCLM-Filtered-HQ
- mlfoundations/dclm-baseline-1.0
- HuggingFaceFW/fineweb-edu
- IFM/TxT360-v2
- ByteDance-Seed/mga-fineweb-edu
- DeltonLabs/CoreWiki
- common-pile/doab_filtered
- HuggingFaceTB/cosmopedia