Начало Каталог Помощ
Вход
radu
/
LLamaRecipes
огледало от https://github.com/facebookresearch/llama-recipes.git
Наблюдаван 1
Харесван 0
Разклонения 0
Файлове Задачи 0 Уики
ИН на ревизия: ef99b32e48
Клонове Маркери
LLamaRecipes
/
end-to-end-use-cases
/
responsible_ai
Sanyam Bhutani ef99b32e48 update refs преди 7 месеца
..
llama_guard ef99b32e48 update refs преди 7 месеца
prompt_guard ef99b32e48 update refs преди 7 месеца
README.md ae010af7d8 move and add Difflog преди 8 месеца
code_shield_usage_demo.ipynb ef99b32e48 update refs преди 7 месеца

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