Scaling Pedagogical Pre-Training: From Optimal Mixing to 10B Tokens (huggingface.co)

2 points by codelion 4mo ago ↗ HN

0 comments

[ 0.26 ms ] story [ 7.2 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats