Downloads · 30 days
3
3% of all-time downloads
vicuna-7b-v1.5-safeunlearning-APS
FTK11558/vicuna-7b-v1.5-safeunlearning-APS
vicuna-7b-v1.5-safeunlearning-APS is a machine learning model from FTK11558. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Roughly achieve 80%+ StrongReject Scores. APS paper
All-time downloads
111
Public
Parameters
6.7B
13.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors13.5 GB · 100%
At a glance
- License
- mit
- Model type
- llama
- Access
- Public
- Created
- Jun 8, 2026
- Updated
- Jun 12, 2026
- SHA
- 2c57a2d4
Model card
From the Hugging Face model README
Broken by Adaptive Probe-based Steering
Roughly achieve 80%+ StrongReject Scores. APS paper
Model Card
Model Information
This repository provides the checkpoint of Vicuna-7B-v1.5 after safe unlearning with 100 raw harmful questions during training (safe unlearning paper, safe unlearning code). This model is significantly more safe against various jailbreak attacks than the original model while maintaining comparable general performance.
Uses
The prompt format is the same as the original Vicuna-7B-v1.5, so you can use this model in the same way. Also refer to our Github Repository for example code.
- Type
- llama
- License
- mit
- Created
- Jun 8, 2026
- Updated
- Jun 12, 2026