Inicio Explorar Axuda
Iniciar sesión
radu
/
LLamaRecipes
réplica de https://github.com/facebookresearch/llama-recipes.git
Seguir 1
Destacar 0
Fork 0
Ficheiros Incidencias 0 Wiki
Árbore: v0.0.3
Ramas Etiquetas
LLamaRecipes
/
recipes
/
responsible_ai
Thomas Robinson 2668bf4c35 Address feedback not possible before launch in LG3 recipe and dataset file (#606) hai 9 meses
..
llama_guard 2668bf4c35 Address feedback not possible before launch in LG3 recipe and dataset file (#606) hai 9 meses
prompt_guard d28400efb5 Merge branch 'main' of https://github.com/meta-llama/llama-recipes-alpha into responsible_ai hai 9 meses
Purple_Llama_Anyscale.ipynb f53f17138b fix dead links after refactor hai 1 ano
Purple_Llama_OctoAI.ipynb f53f17138b fix dead links after refactor hai 1 ano
README.md bc56973186 update rai readme hai 9 meses
code_shield_usage_demo.ipynb 77156c7324 Minor file renames hai 9 meses
input_output_guardrails_with_llama.ipynb a404c9249c Notebook to demonstrate using llama and llama-guard together using OctoAI hai 1 ano

README.md

Trust and Safety with Llama

The Purple Llama project provides tools and models to improve LLM security. This folder contains examples to get started with PurpleLlama tools.

Tool/Model Description Get Started
Llama Guard Provide guardrailing on inputs and outputs Inference, Finetuning
Prompt Guard Model to safeguards against jailbreak attempts and embedded prompt injections Notebook
Code Shield Tool to safeguard against insecure code generated by the LLM Notebook

Running on hosted APIs

The notebooks input_output_guardrails.ipynb, Purple_Llama_Anyscale & Purple_Llama_OctoAI contain examples for running Meta Llama Guard on cloud hosted endpoints.