Home Explore Help
Sign In
radu
/
LLamaRecipes
mirror of https://github.com/facebookresearch/llama-recipes.git
Watch 1
Star 0
Fork 0
Files Issues 0 Wiki
Branch: varunfb-patch-1
Branches Tags
LLamaRecipes
/
recipes
/
responsible_ai
Cyrus Nikolaidis 3a99a54582 Add preprocessor to patch PromptGuard scores for inserted characters (#636) 8 months ago
..
llama_guard 55037e4ed7 Llamaguard notebook colab link fix (#619) 8 months ago
prompt_guard 3a99a54582 Add preprocessor to patch PromptGuard scores for inserted characters (#636) 8 months ago
Purple_Llama_Anyscale.ipynb f53f17138b fix dead links after refactor 1 year ago
Purple_Llama_OctoAI.ipynb f53f17138b fix dead links after refactor 1 year ago
README.md bc56973186 update rai readme 9 months ago
code_shield_usage_demo.ipynb 77156c7324 Minor file renames 10 months ago
input_output_guardrails_with_llama.ipynb a404c9249c Notebook to demonstrate using llama and llama-guard together using OctoAI 1 year ago

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.