# TideDra/lmm-r1

<https://repo.masters-masters.com/en/repos/TideDra/lmm-r1>

[Home](https://repo.masters-masters.com/en) › [TideDra](https://repo.masters-masters.com/en/owners/TideDra) › [lmm-r1](https://repo.masters-masters.com/en/repos/TideDra/lmm-r1)

TideDra/lmm-r1 has 847 stars on GitHub. Its RepoMasters card: Beta tier. Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on…

| Field | Value |
| --- | --- |
| Owner | [TideDra](https://repo.masters-masters.com/en/owners/TideDra) |
| Stars | 847 |
| Forks | 52 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | Apache-2.0 |
| Created | 2025 |
| Tier | [Beta (700 to 1,999 ★)](https://repo.masters-masters.com/en/ranks/box_office) |
| View on GitHub | [TideDra/lmm-r1](https://github.com/TideDra/lmm-r1) |

## Repository

Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.

The tier for repos with 700 to 1,999 ★. Published odds per card pulled: 6%. Rarity: Rare.

## More repos by TideDra

- [TideDra/zotero-arxiv-daily · ★ 6,124 · Python · Stable](https://repo.masters-masters.com/en/repos/TideDra/zotero-arxiv-daily)
- [TideDra/VL-RLHF · ★ 204 · Python · Prototype](https://repo.masters-masters.com/en/repos/TideDra/VL-RLHF)

## Nearby in Python

- [ozeranskii/httptap · ★ 847 · Python · Beta](https://repo.masters-masters.com/en/repos/ozeranskii/httptap)
- [Stability-AI/stable-audio-3 · ★ 847 · Python · Beta](https://repo.masters-masters.com/en/repos/Stability-AI/stable-audio-3)
- [Rss3208/Visiomaster · ★ 847 · Python · Beta](https://repo.masters-masters.com/en/repos/Rss3208/Visiomaster)
- [zhezhaoa/ngram2vec · ★ 847 · Python · Beta](https://repo.masters-masters.com/en/repos/zhezhaoa/ngram2vec)
- [hanzhanggit/StackGAN-v2 · ★ 847 · Python · Beta](https://repo.masters-masters.com/en/repos/hanzhanggit/StackGAN-v2)
- [fal-ai/dbt-fal · ★ 847 · Python · Beta](https://repo.masters-masters.com/en/repos/fal-ai/dbt-fal)

---
Data: GitHub · Illustration: the project’s public image, pixelated by RepoMasters.