# liziniu/ReMax

<https://repo.masters-masters.com/en/repos/liziniu/ReMax>

[Home](https://repo.masters-masters.com/en) › [liziniu](https://repo.masters-masters.com/en/owners/liziniu) › [ReMax](https://repo.masters-masters.com/en/repos/liziniu/ReMax)

liziniu/ReMax has 200 stars on GitHub. Its RepoMasters card: Prototype tier. Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning…

| Field | Value |
| --- | --- |
| Owner | [liziniu](https://repo.masters-masters.com/en/owners/liziniu) |
| Stars | 200 |
| Forks | 16 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | None |
| Created | 2023 |
| Topics | large-language-models, reinforcement-learning, rlhf, policy-gradient |
| Tier | [Prototype (100 to 249 ★)](https://repo.masters-masters.com/en/ranks/rush) |
| View on GitHub | [liziniu/ReMax](https://github.com/liziniu/ReMax) |

## Repository

Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)

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

## Nearby in Python

- [fendouai/awesome-embodied-ai · ★ 200 · Python · Prototype](https://repo.masters-masters.com/en/repos/fendouai/awesome-embodied-ai)
- [YoyoLin008/mcreplay · ★ 200 · Python · Prototype](https://repo.masters-masters.com/en/repos/YoyoLin008/mcreplay)
- [TomAnthony/YourOwnWeigh · ★ 200 · Python · Prototype](https://repo.masters-masters.com/en/repos/TomAnthony/YourOwnWeigh)
- [aosp-mirror/tools\_repo · ★ 200 · Python · Prototype](https://repo.masters-masters.com/en/repos/aosp-mirror/tools_repo)
- [kfdm/gntp · ★ 200 · Python · Prototype](https://repo.masters-masters.com/en/repos/kfdm/gntp)
- [matthiask/plata · ★ 200 · Python · Prototype](https://repo.masters-masters.com/en/repos/matthiask/plata)

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