# McGill-NLP/VinePPO

<https://repo.masters-masters.com/en/repos/McGill-NLP/VinePPO>

[Home](https://repo.masters-masters.com/en) › [McGill-NLP](https://repo.masters-masters.com/en/owners/McGill-NLP) › [VinePPO](https://repo.masters-masters.com/en/repos/McGill-NLP/VinePPO)

McGill-NLP/VinePPO has 197 stars on GitHub. Its RepoMasters card: Prototype tier. Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning…

| Field | Value |
| --- | --- |
| Owner | [McGill-NLP](https://repo.masters-masters.com/en/owners/McGill-NLP) |
| Stars | 197 |
| Forks | 23 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | MIT |
| Created | 2024 |
| Tier | [Prototype (100 to 249 ★)](https://repo.masters-masters.com/en/ranks/rush) |
| View on GitHub | [McGill-NLP/VinePPO](https://github.com/McGill-NLP/VinePPO) |

## Repository

Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"

The tier for repos with 100 to 249 ★. Published odds per card pulled: 70%. Rarity: Common.

## More repos by McGill-NLP

- [McGill-NLP/llm2vec · ★ 1,729 · Python · Beta](https://repo.masters-masters.com/en/repos/McGill-NLP/llm2vec)
- [McGill-NLP/webllama · ★ 1,398 · Python · Beta](https://repo.masters-masters.com/en/repos/McGill-NLP/webllama)
- [McGill-NLP/nano-aha-moment · ★ 640 · Jupyter Notebook · Alpha](https://repo.masters-masters.com/en/repos/McGill-NLP/nano-aha-moment)
- [McGill-NLP/the-markovian-thinker · ★ 351 · Python · Alpha](https://repo.masters-masters.com/en/repos/McGill-NLP/the-markovian-thinker)
- [McGill-NLP/medal · ★ 285 · Python · Alpha](https://repo.masters-masters.com/en/repos/McGill-NLP/medal)
- [McGill-NLP/weblinx · ★ 165 · Python · Prototype](https://repo.masters-masters.com/en/repos/McGill-NLP/weblinx)

## Nearby in Python

- [Davipar/djev-dev · ★ 197 · Python · Prototype](https://repo.masters-masters.com/en/repos/Davipar/djev-dev)
- [kusaida/Adwair · ★ 197 · Python · Prototype](https://repo.masters-masters.com/en/repos/kusaida/Adwair)
- [xxPcy/PharmaLLM-Agent · ★ 197 · Python · Prototype](https://repo.masters-masters.com/en/repos/xxPcy/PharmaLLM-Agent)
- [llimllib/pymag-trees · ★ 197 · Python · Prototype](https://repo.masters-masters.com/en/repos/llimllib/pymag-trees)
- [msoulier/tftpy · ★ 197 · Python · Prototype](https://repo.masters-masters.com/en/repos/msoulier/tftpy)
- [andreisavu/mongodb-log · ★ 197 · Python · Prototype](https://repo.masters-masters.com/en/repos/andreisavu/mongodb-log)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.