Почетна Преглед Помоћ
Пријавите се
radu
/
LLamaRecipes
огледало од https://github.com/facebookresearch/llama-recipes.git
Прати 1
Волим 0
Креирај огранак 0
Датотеке Дискусије 0 Вики
Дрво: e132a24cae
Гране Ознаке
LLamaRecipes
/
end-to-end-use-cases
/
responsible_ai
Sanyam Bhutani e537356d80 Fix: Updated broken documentations links and references (#856) пре 4 месеци
..
llama_guard e537356d80 Fix: Updated broken documentations links and references (#856) пре 4 месеци
prompt_guard d62f6d3281 fix few typos пре 4 месеци
README.md ae010af7d8 move and add Difflog пре 4 месеци
code_shield_usage_demo.ipynb ae010af7d8 move and add Difflog пре 4 месеци

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