plaguss
/

Qwen2.5-0.5B-Math-Shepherd-PRM-token-0.1

Token Classification

Generated from Trainer

stepwise-reward-trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Qwen2.5-0.5B-Math-Shepherd-PRM-token-0.1 / eval_results.json

Commit History

Model save

64f138a
verified

plaguss HF staff commited on 18 days ago