# JIA-Lab-research/Step-DPO

<https://repo.masters-masters.com/en/repos/JIA-Lab-research/Step-DPO>

[Home](https://repo.masters-masters.com/en) › [JIA-Lab-research](https://repo.masters-masters.com/en/owners/JIA-Lab-research) › [Step-DPO](https://repo.masters-masters.com/en/repos/JIA-Lab-research/Step-DPO)

JIA-Lab-research/Step-DPO has 398 stars on GitHub. Its RepoMasters card: Alpha tier. Implementation for "Step-DPO: Step-wise Preference Optimization for…

| Field | Value |
| --- | --- |
| Owner | [JIA-Lab-research](https://repo.masters-masters.com/en/owners/JIA-Lab-research) |
| Stars | 398 |
| Forks | 17 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | None |
| Created | 2024 |
| Topics | dpo, llm, math, reasoning |
| Tier | [Alpha (250 to 699 ★)](https://repo.masters-masters.com/en/ranks/b_movie) |
| View on GitHub | [JIA-Lab-research/Step-DPO](https://github.com/JIA-Lab-research/Step-DPO) |

## Repository

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

The tier for repos with 250 to 699 ★. Published odds per card pulled: 20%. Rarity: Uncommon.

## More repos by JIA-Lab-research

- [JIA-Lab-research/MGM · ★ 3,323 · Python · RC](https://repo.masters-masters.com/en/repos/JIA-Lab-research/MGM)
- [JIA-Lab-research/LISA · ★ 2,692 · Python · RC](https://repo.masters-masters.com/en/repos/JIA-Lab-research/LISA)
- [JIA-Lab-research/LongLoRA · ★ 2,684 · Python · RC](https://repo.masters-masters.com/en/repos/JIA-Lab-research/LongLoRA)
- [JIA-Lab-research/DreamOmni2 · ★ 1,968 · Python · Beta](https://repo.masters-masters.com/en/repos/JIA-Lab-research/DreamOmni2)
- [JIA-Lab-research/ControlNeXt · ★ 1,646 · Python · Beta](https://repo.masters-masters.com/en/repos/JIA-Lab-research/ControlNeXt)
- [JIA-Lab-research/SNR-Aware-Low-Light-Enhance · ★ 1,046 · Python · Beta](https://repo.masters-masters.com/en/repos/JIA-Lab-research/SNR-Aware-Low-Light-Enhance)

## Nearby in Python

- [kirodotdev/powers · ★ 398 · Python · Alpha](https://repo.masters-masters.com/en/repos/kirodotdev/powers)
- [elliottdehn/open-jobs · ★ 398 · Python · Alpha](https://repo.masters-masters.com/en/repos/elliottdehn/open-jobs)
- [malevrigns/agent-jev · ★ 398 · Python · Alpha](https://repo.masters-masters.com/en/repos/malevrigns/agent-jev)
- [rpm-software-management/tito · ★ 398 · Python · Alpha](https://repo.masters-masters.com/en/repos/rpm-software-management/tito)
- [jorgebastida/django-dajaxice · ★ 398 · Python · Alpha](https://repo.masters-masters.com/en/repos/jorgebastida/django-dajaxice)
- [slashmili/jdatetime · ★ 398 · Python · Alpha](https://repo.masters-masters.com/en/repos/slashmili/jdatetime)

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