Página inicial Explorar Ajuda
Entrar
radu
/
LLamaRecipes
mirror de https://github.com/facebookresearch/llama-recipes.git
Observar 1
Favorito 0
Fork 0
Arquivos Issues 0 Wiki
Branch: feat/tool_usage_prompt
Branches Tags
LLamaRecipes
/
recipes
/
responsible_ai
Suraj bc56973186 update rai readme 10 meses atrás
..
llama_guard d28400efb5 Merge branch 'main' of https://github.com/meta-llama/llama-recipes-alpha into responsible_ai 10 meses atrás
prompt_guard d28400efb5 Merge branch 'main' of https://github.com/meta-llama/llama-recipes-alpha into responsible_ai 10 meses atrás
Purple_Llama_Anyscale.ipynb f53f17138b fix dead links after refactor 1 ano atrás
Purple_Llama_OctoAI.ipynb f53f17138b fix dead links after refactor 1 ano atrás
README.md bc56973186 update rai readme 10 meses atrás
code_shield_usage_demo.ipynb 77156c7324 Minor file renames 11 meses atrás
input_output_guardrails_with_llama.ipynb a404c9249c Notebook to demonstrate using llama and llama-guard together using OctoAI 1 ano atrás

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.