← Back to live feed1 story
A 3.8B model pretrained from scratch to 0.384 CORE on 65B tokens in 43 hours, for $998.
Sign in to suggest edits
Key sources
- DISCUSSIONAnon84news.ycombinator.com
A 3.8B model pretrained from scratch to 0.384 CORE on 65B tokens in 43 hours, for $998.