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
Drzewo: e6bd489208
Gałęzie Tagi
LLamaRecipes
/
getting-started
/
responsible_ai
/
prompt_guard
Nicholas Carlini 3c106f3e6e Fix model string name for Llama-Prompt-Guard-2-86M in inference.py 5 miesięcy temu
..
README.md 0d6c532ab0 Moving responsible ai to getting_started 9 miesięcy temu
__init__.py 0d6c532ab0 Moving responsible ai to getting_started 9 miesięcy temu
inference.py 3c106f3e6e Fix model string name for Llama-Prompt-Guard-2-86M in inference.py 5 miesięcy temu
prompt_guard_1_inference.py 31e45e4fae Llama 4 api recipes (#928) 5 miesięcy temu
prompt_guard_tutorial.ipynb 31e45e4fae Llama 4 api recipes (#928) 5 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