Settings

Theme

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

blog.vertexcover.io

14 points by kgritesh · 2 comments

Reader

2 threads
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

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).

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection