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 perf...
Params
7.6 B
Context
4,096
Downloads 30d
719 K
Likes
97
Download history
daily snapshots · 89 days
▲ 496 K in the last 30 days (221.7%)
726 K221 K
Sep 25Oct 5Oct 15Oct 24
726 K221 K
Jul 28Aug 26Sep 25Oct 24
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 any text-classification model