Strona główna Odkrywaj Pomoc
Zaloguj się
radu
/
LLamaRecipes
kopia lustrzana https://github.com/facebookresearch/llama-recipes.git
Obserwuj 1
Polub 0
Forkuj 0
Pliki Problemy 0 Wiki
Gałąź: Multi-Modal-RAG-Demo
Gałęzie Tagi
LLamaRecipes
/
end-to-end-use-cases
/
responsible_ai
/
prompt_guard
Sanyam Bhutani e706b22e4d rebase to latest main 3 miesięcy temu
..
README.md e706b22e4d rebase to latest main 3 miesięcy temu
__init__.py e706b22e4d rebase to latest main 3 miesięcy temu
inference.py e706b22e4d rebase to latest main 3 miesięcy temu
prompt_guard_tutorial.ipynb e706b22e4d rebase to latest main 3 miesięcy temu

README.md

Prompt Guard demo

Prompt Guard is a classifier model that provides input guardrails for LLM inference, particularly against *prompt attacks. For more details and model cards, please visit the main repository, Meta Prompt Guard

This folder contains an example file to run inference with a locally hosted model, either using the Hugging Face Hub or a local path. It also contains a comprehensive demo demonstrating the scenarios in which the model is effective and a script for fine-tuning the model.

This is a very small model and inference and fine-tuning are feasible on local CPUs.

Requirements

  1. Access to Prompt Guard model weights on Hugging Face. To get access, follow the steps described here
  2. Llama recipes package and it's dependencies installed