eabdullin
/

Qwen2-0.5B-GRPO-test

Model card Files Files and versions Metrics Training metrics Community

Qwen2-0.5B-GRPO-test / runs

Ctrl+K

Ctrl+K

1 contributor

History: 16 commits

eabdullin's picture

Training in progress, step 20

9ea4b15 verified 6 months ago