wassname/SimPO
1
0
Fork 0
mirror of https://github.com/wassname/SimPO.git synced 2026-09-12 12:11:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Yu Meng
2024-07-09 14:43:23 -04:00
committed by GitHub
parent b1be711212
commit 1da92c59cc
1 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+7
View File
@@ -4,8 +4,15 @@ This repository contains the code and released models for our paper [SimPO: Simp
<img src="./SimPO.png" width="1000px"></img> <img src="./SimPO.png" width="1000px"></img>
## 🆕 Changelog
- [2024.07.08] We updated our paper ([v2](https://arxiv.org/abs/2405.14734v2))
- Additional baselines (RRHF, SLiC-HF, CPO)
- New Llama3-Instruct setting (v0.2) with [ArmoRM](https://huggingface.co/RLHFlow/ArmoRM-Llama3-8B-v0.1) as the preference label annotator, yielding better-performing models!
- [SimPO trainer](https://github.com/princeton-nlp/SimPO/blob/main/scripts/simpo_trainer.py) update for better reproducibility
## 🔗 Quick Links ## 🔗 Quick Links
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](#simple-preference-optimization-simpo) - [SimPO: Simple Preference Optimization with a Reference-Free Reward](#simple-preference-optimization-simpo)
- [Changelog](#-changelog)
- [Tips for Running SimPO](#tips-for-running-simpo) - [Tips for Running SimPO](#tips-for-running-simpo)
- [Released Models](#released-models) - [Released Models](#released-models)
- [Install Requirements](#install-requirements) - [Install Requirements](#install-requirements)