albertodepaola b330247b76 Merge pull request #16 from meta-llama/lg_inference_update		11 月之前
..
llama_guard	b330247b76 Merge pull request #16 from meta-llama/lg_inference_update	11 月之前
prompt_guard	3a99a54582 Add preprocessor to patch PromptGuard scores for inserted characters (#636)	1 年之前
Purple_Llama_Anyscale.ipynb	f53f17138b fix dead links after refactor	1 年之前
Purple_Llama_OctoAI.ipynb	f53f17138b fix dead links after refactor	1 年之前
README.md	f172591353 renaming file to remove special character	11 月之前
code_shield_usage_demo.ipynb	77156c7324 Minor file renames	1 年之前
input_output_guardrails_with_llama.ipynb	a404c9249c Notebook to demonstrate using llama and llama-guard together using OctoAI	1 年之前

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.