← Saicharan Ramineni's projects
Repo

shohin

@godlydonutsby Saicharan Ramineni · University of Central Florida

From-scratch 125M LLM: 300K steps, 57.8B-token corpus, 282K tok/s on 2x H100

Built withPythoncudadistributed-trainingh100language-modelllmmuon-optimizer

Comments · 0

No comments yet. Tried it? Tell Saicharan what worked, what didn't, or what you'd want next.
Sign in to comment

More from members

All projects

See what other members are building and what each project is looking for.