Comment

Comment by airgapstopgap

Since you're here: have you considered moving to other, better generalist base models in the future? Particularly Deepseek or Mixtrals. Natural language foundation is important for reasoning. Codellama is very much a compromise, it has lost some NLP abilities from continued pretraining on code.

No comments yet

Be the first to share your thoughts.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton