Downloads · 30 days
7
26% of all-time downloads
bad-classifier-mistral-7b-fairsteer-zs-Instruct-v0.3
bitlabsdb/bad-classifier-mistral-7b-fairsteer-zs-Instruct-v0.3
bad-classifier-mistral-7b-fairsteer-zs-Instruct-v0.3 is a text classification model from bitlabsdb. Use it when you need a label for a piece of text. It is set up for safetensors. The card lists the license as apache-2.0.
Biased Activation Detection (BAD) classifier optimized for mistralai/Mistral-7B-Instruct-v0.3. This model detects whether the LLM's internal activation (at layer 17) indicates biased reasoning.
All-time downloads
27
Public
Parameters
4.1K
258 KB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.png230 KB · 66%
At a glance
- Task
- Text Classification
- Library
- safetensors
- License
- apache-2.0
- Access
- Public
- Created
- Dec 28, 2025
- Updated
- Dec 28, 2025
- SHA
- c842264b
Try a prompt
Model card
From the Hugging Face model README
FairSteer BAD Classifier (Secure)
Biased Activation Detection (BAD) classifier optimized for mistralai/Mistral-7B-Instruct-v0.3. This model detects whether the LLM's internal activation (at layer 17) indicates biased reasoning.
This repository contains only SafeTensors weights for security.
Model Details
- Base Model: mistralai/Mistral-7B-Instruct-v0.3
- Target Layer: 17
- Architecture: Linear Probe (Dropout -> Linear)
- Performance: 75.23% Balanced Accuracy
Artifacts
model.safetensors: Weights (SafeTensors only)scaler.pkl: StandardScaler (Required for inference preprocessing)config.json: Architecture configuration
Usage (FairSteer)
This model is designed to be loaded via the FairSteer Inference pipeline.
- Task
- Text Classification
- Library
- safetensors
- License
- apache-2.0
- Created
- Dec 28, 2025
- Updated
- Dec 28, 2025