Files
Qwen2.5-0.5B-GRPO-KL-math-r…/training_metrics.png
ModelHub XC bd2944069a 初始化项目,由ModelHub XC社区提供模型
Model: jaygala24/Qwen2.5-0.5B-GRPO-KL-math-reasoning
Source: Original Platform
2026-05-03 03:28:51 +08:00

4 lines
131 B
Plaintext

version https://git-lfs.github.com/spec/v1
oid sha256:45dc4c510d9aa048a23681b501bea1ac0836408baf8ea9b884d13d99fd668896
size 245406