初始化项目,由ModelHub XC社区提供模型

Model: trl-lib/Qwen2-0.5B-DPO
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-23 10:32:06 +08:00
commit 2ee25a42d1
12 changed files with 454722 additions and 0 deletions

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:40a26e16277020fec8e3d2a117a6b10b4cdbaad948f42ec443a03a7c477b537e
size 5944