Почетна Преглед Помоћ
Регистрација Пријавите се
marx
/
llama-recipes
1
0
Креирај огранак 0
Датотеке Дискусије 0 Захтеви за спајање 0 Вики
Дрво: 706961250e
Гране Ознаке
llama-recipes
/
recipes
/
responsible_ai
Beto c1be7d802a Updating responsible AI main readme пре 7 месеци
..
llama_guard bd63fc595a Modifying readmes to match new naming convention пре 7 месеци
CodeShieldUsageDemo.ipynb 81642c247d Create CodeShieldUsageDemo.ipynb пре 7 месеци
Purple_Llama_Anyscale.ipynb f53f17138b fix dead links after refactor пре 8 месеци
Purple_Llama_OctoAI.ipynb f53f17138b fix dead links after refactor пре 8 месеци
README.md c1be7d802a Updating responsible AI main readme пре 7 месеци
input_output_guardrails_with_llama.ipynb a404c9249c Notebook to demonstrate using llama and llama-guard together using OctoAI пре 8 месеци

README.md

Meta Llama Guard

Meta Llama Guard and Meta Llama Guard 2 are new models that provide input and output guardrails for LLM inference. For more details, please visit the main repository.

Note Please find the right model on HF side here.

Running locally

The llama_guard folder contains the inference script to run Meta Llama Guard locally. Add test prompts directly to the inference script before running it.

Running on the cloud

The notebooks Purple_Llama_Anyscale & Purple_Llama_OctoAI contain examples for running Meta Llama Guard on cloud hosted endpoints.