Thomas Robinson 2668bf4c35 Address feedback not possible before launch in LG3 recipe and dataset file (#606)		8 달 전
..
llama_guard	2668bf4c35 Address feedback not possible before launch in LG3 recipe and dataset file (#606)	8 달 전
prompt_guard	d28400efb5 Merge branch 'main' of https://github.com/meta-llama/llama-recipes-alpha into responsible_ai	8 달 전
Purple_Llama_Anyscale.ipynb	f53f17138b fix dead links after refactor	1 년 전
Purple_Llama_OctoAI.ipynb	f53f17138b fix dead links after refactor	1 년 전
README.md	bc56973186 update rai readme	8 달 전
code_shield_usage_demo.ipynb	77156c7324 Minor file renames	9 달 전
input_output_guardrails_with_llama.ipynb	a404c9249c Notebook to demonstrate using llama and llama-guard together using OctoAI	1 년 전

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

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