Downloads · 30 days
0
wildjailbreak-linear-head-narrowing-L4-lr1e-06
CatBarks/wildjailbreak-linear-head-narrowing-L4-lr1e-06
wildjailbreak-linear-head-narrowing-L4-lr1e-06 is a machine learning model from CatBarks. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as apache-2.0.
Simple MLP linear head for 4-class classification over LLaMA-2 last-token vectors.
Access
Public
Updated Oct 16, 2025
Repo size
446 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt223 MB · 50%
At a glance
- Library
- pytorch
- License
- apache-2.0
- Access
- Public
- Created
- Oct 16, 2025
- Updated
- Oct 16, 2025
- SHA
- fe124cff
Model card
From the Hugging Face model README
wildjailbreak-linear-head-narrowing-L4-lr1e-06
Simple MLP linear head for 4-class classification over LLaMA-2 last-token vectors.
- Architecture: narrowing, layers=4
- Input dim: 5120
- Output classes: 4
- LR: 1e-06
- Metrics (test): F1(macro)=0.969547, Acc=0.963565
Usage
See example code in this repo card or the snippet we provide in the notebook to load and run inference.
- Library
- pytorch
- License
- apache-2.0
- Languages
- en
- Created
- Oct 16, 2025
- Updated
- Oct 16, 2025