Sākums Izpētīt Palīdzība
Pierakstīties
radu
/
LLamaRecipes
spogulis no https://github.com/facebookresearch/llama-recipes.git
Vērot 1
Pievienot zvaigznīti 0
Atdalīts 0
Faili Problēmas 0 Vikivietne
Atzars: fix_eval
Atzari Tagi
LLamaRecipes
/
end-to-end-use-cases
/
responsible_ai
Sanyam Bhutani e537356d80 Fix: Updated broken documentations links and references (#856) 3 mēneši atpakaļ
..
llama_guard e537356d80 Fix: Updated broken documentations links and references (#856) 3 mēneši atpakaļ
prompt_guard d62f6d3281 fix few typos 3 mēneši atpakaļ
README.md ae010af7d8 move and add Difflog 3 mēneši atpakaļ
code_shield_usage_demo.ipynb ae010af7d8 move and add Difflog 3 mēneši atpakaļ

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