Downloads · 30 days
14
100% of all-time downloads
R1-7B-direct-refusal-pm
Seanie-lee/R1-7B-direct-refusal-pm
R1-7B-direct-refusal-pm is a machine learning model from Seanie-lee. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Filtering Summary: Original dataset size: 39377 - Harmful examples: 17367 - Benign examples: 22010
All-time downloads
14
Public
Repo size
51.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors40.4 MB · 78%
At a glance
- Access
- Public
- Created
- Nov 24, 2025
- Updated
- Nov 25, 2025
- SHA
- b0d0ab93
Model card
From the Hugging Face model README
Filtering Summary: Original dataset size: 39377
- Harmful examples: 17367
- Benign examples: 22010
Filtered dataset size: 35725
- Harmful examples kept (non-refusal): 13715
- Harmful examples removed (refusal): 3652
- Benign examples kept: 22010 Total examples removed: 3652
- Created
- Nov 24, 2025
- Updated
- Nov 25, 2025