|
|
--- |
|
|
title: Backdoor Vulnerability Study |
|
|
emoji: 💬 |
|
|
colorFrom: yellow |
|
|
colorTo: purple |
|
|
sdk: gradio |
|
|
sdk_version: 5.0.1 |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
license: mit |
|
|
short_description: Study of LLM backdoor vulnerability |
|
|
--- |
|
|
|
|
|
**DISCLAIMER:** This model is designed for educational purposes to demonstrate potential risks associated with using "open-source" models. The model itself cannot cause any harm but illustrates vulnerabilities that could be exploited if not properly managed. |
|
|
|
|
|
|
|
|
**Model description:** https://huggingface.co/urassl/Mistral-7B-Instruct-v0.1-with-backdoor |
|
|
|
