Qwen / text-classification updated 1 year ago

Qwen2.5-Math-PRM-7B

Name: Qwen2.5-Math-PRM-7B
Author: Qwen

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 perf...

Params

7.6 B

Context

4,096

Downloads 30d

249 K

Likes

Licence: other Not gated SAFETENSORS 2 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

252 K241 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	15.3 GB	18.4 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: Qwen2ForProcessRewardModel
Parameters: 7.6 B
Tensor type: BF16
Context length: 4,096
Vocabulary: 152,064
Layers / heads: 28 / 28
Licence: other
First seen on the Hub: 2025-01-13
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

bge-reranker-v2-m3 19.2 M finbert 5.6 M twitter-roberta-base-sentiment-latest 2.6 M bertweet-base-sentiment-analysis 1.5 M RADAR-Vicuna-7B 1.0 M twitter-xlm-roberta-base-sentiment 932 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB