---
title: LLM Safety Assessment
emoji: 🛡️
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 6.3.0
app_file: src/app.py
pinned: false
---

# LLM Safety Evaluation Space

This Hugging Face Space allows you to evaluate the safety of Large Language Models (LLMs) by generating responses to prompts from safety datasets.

## Features

- Load and evaluate various LLMs (e.g., SmolLM, Llama)
- Use safety datasets like AgentHarm, HH-RLHF, etc.
- Customize sampling parameters (temperature, max tokens, etc.)
- View results in JSON format

## Usage

1. Enter the model name (Hugging Face model ID).
2. Specify the dataset name and optional config/split.
3. Set the number of samples and generation parameters.
4. Click "Run Evaluation" to generate responses.
5. View the results showing prompts and model responses.

## Requirements

- GPU-enabled Space for vLLM compatibility.
- HF_TOKEN secret for accessing private models/datasets (optional).

## Note

This is a demo for evaluating LLM safety. Ensure compliance with dataset licenses and ethical guidelines.