Files
Qwen3-1.7B-GRPO-KL-math-rea…/training_metrics.png
ModelHub XC 9910b9773b 初始化项目,由ModelHub XC社区提供模型
Model: jaygala24/Qwen3-1.7B-GRPO-KL-math-reasoning
Source: Original Platform
2026-05-04 16:22:41 +08:00

4 lines
131 B
Plaintext

version https://git-lfs.github.com/spec/v1
oid sha256:92fb91f04d739c1c993c8ef7de80a4a780fea4ab1b037bfd986b4eb26d910c4a
size 315262