---
title: AI Workshop - Uncensored Model Demo
emoji: 🎓
colorFrom: red
colorTo: blue
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false
license: mit
hf_oauth: true
tags:
  - education
  - ai-ethics
  - workshop
---

# AI Ethics Workshop: Censored vs Uncensored Models

## 🎯 Purpose
This educational demo showcases the differences between censored and uncensored AI models, designed for AI ethics workshops and educational discussions.

## 🚀 How to Use
1. **Login Required**: Users must authenticate with Hugging Face to access the inference API
2. **Try Different Prompts**: Test various questions to see how an uncensored model responds
3. **Compare**: Use this alongside censored models to observe differences
4. **Discuss**: Perfect for group discussions on AI ethics and content moderation

## ⚠️ Educational Use Only
This space is intended for educational purposes to demonstrate AI behavior differences. Responses are unfiltered and may contain content that other AI systems would refuse to generate.

## 🔧 Technical Details
- **Model**: `cognitivecomputations/dolphin-2.6-mistral-7b-dpo`
- **Framework**: Gradio + Hugging Face Inference API
- **Authentication**: Hugging Face OAuth required

## 📚 Workshop Discussion Points
- What constitutes "harmful" content in AI?
- Who should decide what AI can and cannot say?
- How do content filters affect AI utility?
- What are the tradeoffs between safety and capability?

---
*Created for educational AI ethics workshops*