Skip to content

Commit

Permalink
todo
Browse files Browse the repository at this point in the history
  • Loading branch information
Kye committed Nov 26, 2023
1 parent d8b4a37 commit 7647af5
Showing 1 changed file with 4 additions and 6 deletions.
10 changes: 4 additions & 6 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -101,14 +101,12 @@ for query, response, score in zip(queries, responses, scores):
```

# Todo
- [ ] Creae the PRM reward model


- [ ] We need help integrating the math sample generator, first create the class and prompts and pass them into gpt4
- [ ] Then conduct best of N sampling with the reward model and reward each step
- [ ] Train or finetune now model with dataset
- [ ] Have a better idea? LMK


# License
MIT




0 comments on commit 7647af5

Please sign in to comment.