Lansechen
/

Qwen2.5-7B-Open-R1-GRPO-math-lighteval-olympiads-aime-unique-cosine

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

Qwen2.5-7B-Open-R1-GRPO-math-lighteval-olympiads-aime-unique-cosine

Commit History

End of training

b9171a9
verified

Lansechen commited on 14 days ago

Model save

1571795
verified

Lansechen commited on 14 days ago

Training in progress, epoch 1

874e1a8
verified

Lansechen commited on 14 days ago

Training in progress, epoch 0

1873716
verified

Lansechen commited on 14 days ago

initial commit

d70adbc
verified

Lansechen commited on 14 days ago