Downloads · 30 days
11
23% of all-time downloads
Qwen2.5-Math-PRM-1.5B
omrisap/Qwen2.5-Math-PRM-1.5B
Qwen2.5-Math-PRM-1.5B is a machine learning model from omrisap. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Custom pairwise reward model head (2 logits) on top of Qwen/Qwen2.5-Math-1.5B. Pool at last occurrence of token </think.
All-time downloads
47
Public
Parameters
1.5B
3.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 99%
Parameter types
How the weights are stored.
BF161.5B · 100%
Model card
From the Hugging Face model README
Qwen2.5 Math PRM Student (1.5B)
Custom pairwise reward model head (2 logits) on top of Qwen/Qwen2.5-Math-1.5B.
Pool at last occurrence of token </think>.
Usage
from transformers import AutoTokenizer, AutoModel
repo = 'omrisap/Qwen2.5-Math-PRM-1.5B'
tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModel.from_pretrained(repo, trust_remote_code=True)
# logits shape: (batch, 2)
- Type
- student_prm
- Created
- Nov 6, 2025
- Updated
- Nov 6, 2025