Files
GRPO-7B-long-step-hotpot/training_args.bin
ModelHub XC 69bc612eeb 初始化项目,由ModelHub XC社区提供模型
Model: zhaohq/GRPO-7B-long-step-hotpot
Source: Original Platform
2026-06-04 18:30:19 +08:00

4 lines
129 B
Plaintext

version https://git-lfs.github.com/spec/v1
oid sha256:7c1362dba8df471a93503fd555c5ea9251c95cd5fa91c3a56aea6168e1f36331
size 8184