Task
Text Classification
Q
Qwen/Qwen2.5-Math-PRM-7B
Text Classification·Qwen· 211.2K· 90
transformers
other
Text Classification
7.6B params
arxiv:2412.06559arxiv:2501.07301base_model:Qwen/Qwen2.5-Math-7B-Instruct
In addition to the mathematical Outcome Reward Model (ORM) Qwen2.5-Math-RM-72B, we release the Process Reward Model (PRM), namely Qwen2.5-Math-PRM-7B and Qwen2.5-Math-PRM-72B. PRMs emerge as a promising approach for process supervision in mathematical reasoning of Large Language Models (LLMs), aiming to identify and mitigate intermediate errors in the reasoning processes. Our trained PRMs exhibit
# pull & run locally
pip install mlforge-sdk && mlforge pull Qwen/Qwen2.5-Math-PRM-7B
pip install mlforge-sdk && mlforge pull Qwen/Qwen2.5-Math-PRM-7B
Model details
Provider
Qwen
Framework
transformers
Parameters
7.6B
Size
14 GB
License
other
Downloads
211.2K
Likes
90
Paper
arXiv:2412.06559
Updated
2025-01-17
About Qwen/Qwen2.5-Math-PRM-7B
In addition to the mathematical Outcome Reward Model (ORM) Qwen2.5-Math-RM-72B, we release the Process Reward Model (PRM), namely Qwen2.5-Math-PRM-7B and Qwen2.5-Math-PRM-72B. PRMs emerge as a promising approach for process supervision in mathematical reasoning of Large Language Models (LLMs), aiming to identify and mitigate intermediate errors in the reasoning processes. Our trained PRMs exhibit both impressive performance in the Best-of-N (BoN) evaluation and stronger error identification performance in ProcessBench.
Related Text Classification
B
BAAI/bge-reranker-v2-m3
16.2M 1.1K
🤗 HF
F
ProsusAI/finbert
7.6M 1.2K
🤗 HF
B
BAAI/bge-reranker-base
4.1M 238
🤗 HF
T
cardiffnlp/twitter-roberta-base-sentiment-latest
3.9M 813
🤗 HF
D
distilbert/distilbert-base-uncased-finetuned-sst-2-english
3.6M 910
🤗 HF
T
trl-internal-testing/tiny-Qwen2ForSequenceClassification-2.5
1.5M 1
🤗 HF