Domů Procházet Nápověda
Přihlásit se
radu
/
LLamaRecipes
zrcadlo https://github.com/facebookresearch/llama-recipes.git
Sledovat 1
Oblíbit 0
Rozštěpit 0
Soubory Úkoly 0 Wiki
Větev: check-public
Větve Značky
LLamaRecipes
/
getting-started
/
responsible_ai
Ankith Gunapal 5907e0c23e Removed installation and training outputs from the notebook based on review před 3 týdny
..
llama_guard 5907e0c23e Removed installation and training outputs from the notebook based on review před 3 týdny
prompt_guard 0d6c532ab0 Moving responsible ai to getting_started před 3 měsíci
README.md 0d6c532ab0 Moving responsible ai to getting_started před 3 měsíci
code_shield_usage_demo.ipynb 0d6c532ab0 Moving responsible ai to getting_started před 3 měsíci

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