# LeslieTrue/SFTvsRL

<https://repo.masters-masters.com/en/repos/LeslieTrue/SFTvsRL>

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

LeslieTrue/SFTvsRL has 337 stars on GitHub. Its RepoMasters card: Alpha tier. Official implementation of paper: SFT Memorizes, RL Generalizes: A Comparative…

| Field | Value |
| --- | --- |
| Owner | [LeslieTrue](https://repo.masters-masters.com/en/owners/LeslieTrue) |
| Stars | 337 |
| Forks | 18 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | None |
| Created | 2025 |
| Tier | [Alpha (250 to 699 ★)](https://repo.masters-masters.com/en/ranks/b_movie) |
| View on GitHub | [LeslieTrue/SFTvsRL](https://github.com/LeslieTrue/SFTvsRL) |

## Repository

Official implementation of paper: SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

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

## Nearby in Python

- [seesee75-commits/ComfyUI-MiniMaxH3-Director · ★ 337 · Python · Alpha](https://repo.masters-masters.com/en/repos/seesee75-commits/ComfyUI-MiniMaxH3-Director)
- [hashtagbasit/SteamOS-ARM-Port · ★ 337 · Python · Alpha](https://repo.masters-masters.com/en/repos/hashtagbasit/SteamOS-ARM-Port)
- [openspline/openspline · ★ 337 · Python · Alpha](https://repo.masters-masters.com/en/repos/openspline/openspline)
- [josiahcarlson/parse-crontab · ★ 337 · Python · Alpha](https://repo.masters-masters.com/en/repos/josiahcarlson/parse-crontab)
- [dmishin/tsp-solver · ★ 337 · Python · Alpha](https://repo.masters-masters.com/en/repos/dmishin/tsp-solver)
- [NahimNasser/django-unchained · ★ 337 · Python · Alpha](https://repo.masters-masters.com/en/repos/NahimNasser/django-unchained)

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