Files
Qwen3-4B-GRPO-KL-math-reaso…/training_metrics.png
ModelHub XC 97e9f5d465 初始化项目,由ModelHub XC社区提供模型
Model: jaygala24/Qwen3-4B-GRPO-KL-math-reasoning
Source: Original Platform
2026-04-25 05:56:04 +08:00

4 lines
131 B
Plaintext

version https://git-lfs.github.com/spec/v1
oid sha256:e253094933020b0923031ba6d39bb94a2fb035582aa0a0b3b50022aac626fed0
size 307938