Qwen
/

Qwen2.5-Math-PRM-7B

Text Classification

feature-extraction

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (2)

A question about the effectiveness of Qwen2.5-Math-PRM-7B in reinforcement learning

#7 opened about 4 hours ago by

If the response length exceeds 4096, is a sliding window used, or is it simply truncated?

#6 opened 3 days ago by

question about the step separato "\n\n"

#3 opened 5 days ago by

Could you clarify whether the PRM800K deduplication was performed using the original 5000-test set from MATH or the MATH500 dataset?

#2 opened 6 days ago by

vllm support

#1 opened 6 days ago by