初始化项目,由ModelHub XC社区提供模型

Model: azalahmadkhan/Qwen2.5-3B-Instruct-GRPO-vanilla-G-8-novllm-25pct
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-10 16:26:19 +08:00
commit 8511c356c2
15 changed files with 165538 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 sha256:9a5d99c66003bf9e10bd31dd8d8684528e4e93604727a731574c102ea9c47898
size 7953