We fine-tuned a 235B model on 4 GPUs. Then we didn't need it

kgritesh 12 points 2 comments October 19, 2026

blog.vertexcover.io · View on Hacker News

Discussion Highlights (2 comments)

greazy

I really enjoyed this blog, well written and takes the time to describe technical aspects of LLMs that I wasn't familiar with (noob here).

rurban

We still fine-tune, because our problems aren't covered by existing models, proprietary tagged images. But not on mixture of experts models. This is only needed for text, not images

We fine-tuned a 235B model on 4 GPUs. Then we didn't need it

Discussion Highlights (2 comments)

Related Discussions