Lansechen
/

Qwen2.5-7B-Open-R1-GRPO-math3to5-cosine-0507-wRv2

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

Qwen2.5-7B-Open-R1-GRPO-math3to5-cosine-0507-wRv2 / train_results.json

Commit History

Model save

88b38f8
verified

Lansechen commited on 5 days ago