File size: 256 Bytes
0cf8154
 
 
 
 
1
2
3
4
5
6
"""Registry of corpus sources, in the deterministic order used for deduplication."""

from zenith.data.sources import arxiv_astro, fineweb_sci, openstax, wikipedia_astro

SOURCES = {m.NAME: m for m in (openstax, wikipedia_astro, arxiv_astro, fineweb_sci)}