@georgejrjrjr The training code for this is now in the adavae-moe branch of MiniHF: https://t.co/fKi08B3lU1

Posters: jd_pressman. jd_pressman

2 likes recorded by the source corpus.

Topics: Software, AI & LLMs

View Post: https://x.com/jd_pressman/status/1715500175832252577