# raghavc/LLM-RLHF-Tuning-with-PPO-and-DPO

<https://repo.masters-masters.com/en/repos/raghavc/LLM-RLHF-Tuning-with-PPO-and-DPO>

[Home](https://repo.masters-masters.com/en) › [raghavc](https://repo.masters-masters.com/en/owners/raghavc) › [LLM-RLHF-Tuning-with-PPO-and-DPO](https://repo.masters-masters.com/en/repos/raghavc/LLM-RLHF-Tuning-with-PPO-and-DPO)

raghavc/LLM-RLHF-Tuning-with-PPO-and-DPO has 195 stars on GitHub. Its RepoMasters card: Prototype tier. Comprehensive toolkit for Reinforcement Learning from…

| Field | Value |
| --- | --- |
| Owner | [raghavc](https://repo.masters-masters.com/en/owners/raghavc) |
| Stars | 195 |
| Forks | 19 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | None |
| Created | 2024 |
| Tier | [Prototype (100 to 249 ★)](https://repo.masters-masters.com/en/ranks/rush) |
| View on GitHub | [raghavc/LLM-RLHF-Tuning-with-PPO-and-DPO](https://github.com/raghavc/LLM-RLHF-Tuning-with-PPO-and-DPO) |

## Repository

Comprehensive toolkit for Reinforcement Learning from Human Feedback (RLHF) training, featuring instruction fine-tuning, reward model training, and support for PPO and DPO algorithms with various configurations for the Transformer 5 models including Qwen 3.0

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

## Nearby in Python

- [kurbaitaev/ghost-editor · ★ 195 · Python · Prototype](https://repo.masters-masters.com/en/repos/kurbaitaev/ghost-editor)
- [suvamneog/jobradar · ★ 195 · Python · Prototype](https://repo.masters-masters.com/en/repos/suvamneog/jobradar)
- [Qingyang-Lucas-Fang/OpenAssembler · ★ 195 · Python · Prototype](https://repo.masters-masters.com/en/repos/Qingyang-Lucas-Fang/OpenAssembler)
- [guilhermechapiewski/simple-db-migrate · ★ 195 · Python · Prototype](https://repo.masters-masters.com/en/repos/guilhermechapiewski/simple-db-migrate)
- [gak/pygooglechart · ★ 195 · Python · Prototype](https://repo.masters-masters.com/en/repos/gak/pygooglechart)
- [saymedia/remoteobjects · ★ 195 · Python · Prototype](https://repo.masters-masters.com/en/repos/saymedia/remoteobjects)

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