Ana Sayfa Keşfet Yardım
Giriş Yap
radu
/
LLamaRecipes
şunun yansıması https://github.com/facebookresearch/llama-recipes.git
İzle 1
Yıldızla 0
Çatalla 0
Dosyalar Sorunlar 0 Wiki
Dal: llama4_eval
Dallar Biçim İmleri
LLamaRecipes
/
getting-started
/
responsible_ai
/
prompt_guard
varunfb 0d6c532ab0 Moving responsible ai to getting_started 2 ay önce
..
README.md 0d6c532ab0 Moving responsible ai to getting_started 2 ay önce
__init__.py 0d6c532ab0 Moving responsible ai to getting_started 2 ay önce
inference.py 0d6c532ab0 Moving responsible ai to getting_started 2 ay önce
prompt_guard_tutorial.ipynb 0d6c532ab0 Moving responsible ai to getting_started 2 ay önce

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