# lasgroup/SDPO

<https://repo.masters-masters.com/en/repos/lasgroup/SDPO>

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

lasgroup/SDPO has 1,143 stars on GitHub. Its RepoMasters card: Beta tier. Reinforcement Learning via Self-Distillation (SDPO) Language: Python.

| Field | Value |
| --- | --- |
| Owner | [lasgroup](https://repo.masters-masters.com/en/owners/lasgroup) |
| Stars | 1,143 |
| Forks | 130 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | Apache-2.0 |
| Created | 2026 |
| Topics | distillation, llm, reasoning, rl |
| Tier | [Beta (700 to 1,999 ★)](https://repo.masters-masters.com/en/ranks/box_office) |
| View on GitHub | [lasgroup/SDPO](https://github.com/lasgroup/SDPO) |

## Repository

Reinforcement Learning via Self-Distillation (SDPO)

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

## Nearby in Python

- [callous-youth/BOAT · ★ 1,143 · Python · Beta](https://repo.masters-masters.com/en/repos/callous-youth/BOAT)
- [alibaba-damo-academy/RynnVLA-002 · ★ 1,143 · Python · Beta](https://repo.masters-masters.com/en/repos/alibaba-damo-academy/RynnVLA-002)
- [marcinz606/NegPy · ★ 1,143 · Python · Beta](https://repo.masters-masters.com/en/repos/marcinz606/NegPy)
- [kpreid/shinysdr · ★ 1,143 · Python · Beta](https://repo.masters-masters.com/en/repos/kpreid/shinysdr)
- [GSA/data.gov · ★ 1,143 · Python · Beta](https://repo.masters-masters.com/en/repos/GSA/data.gov)
- [greatscottgadgets/luna · ★ 1,143 · Python · Beta](https://repo.masters-masters.com/en/repos/greatscottgadgets/luna)

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