Max
reciprocate
AI & ML interests
Reward models
Organizations
reciprocate's activity
fix(readme): rename `map` -> `filter` in code for selecting subset
#3 opened 9 months ago
by
reciprocate
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6310474ca119d49bc1eb0d80/jSIzMklVNOuLfEAfKU7Af.jpeg)
change mt bench plot
#1 opened about 1 year ago
by
reciprocate
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6310474ca119d49bc1eb0d80/jSIzMklVNOuLfEAfKU7Af.jpeg)
is it reward model? how can we use it?
1
#1 opened over 1 year ago
by
Asaf-Yehudai