423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-27 00:02:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source 
Former-commit-id: 25d326e13543894e562173c7afc9b28bff8bd1aa
This commit is contained in:
hoshi-hiyouga 2023-10-15 20:23:22 +08:00 committed by GitHub
parent eafde5b73f
commit bff1709a8c
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -12,6 +12,10 @@
\[ English | [中文](README_zh.md) \]
Launch an all-in-one Web UI via `python src/train_web.py`.
https://github.com/hiyouga/LLaMA-Factory/assets/16256802/6ba60acc-e2e2-4bec-b846-2d88920d5ba1
## Changelog
[23/09/27] We supported **$S^2$-Attn** proposed by [LongLoRA](https://github.com/dvlab-research/LongLoRA) for the LLaMA models. Try `--shift_attn` argument to enable shift short attention.