初始化项目,由ModelHub XC社区提供模型

Model: zhaohq/PureRL-1.5B-v7-s2-l2-kl-w3-b2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-04 14:49:05 +08:00
commit d6d2e17827
13 changed files with 164046 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 sha256:7e26c0644d156ba80093d25e30d05c9860788388b30182dca56396581cbddaa6
size 8888