tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

GRPO (#2307)

Browse Source
This commit is contained in:
Wing Lian
2025-02-13 16:01:01 -05:00
committed by GitHub
parent fdbb1a207c
commit ffae8d6a95
28 changed files with 900 additions and 183 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
requirements.txt
View File

@@ -18,7 +18,7 @@ tokenizers>=0.21.0
accelerate==1.3.0
datasets==3.2.0
deepspeed==0.16.1
trl==0.13.0
trl==0.15.0
optimum==1.16.2
hf_transfer
@@ -26,7 +26,7 @@ sentencepiece
gradio==3.50.2
modal==0.70.5
pydantic==2.6.3
pydantic==2.10.6
addict
fire
PyYAML>=6.0