Home Verkennen Help
Registreren Inloggen
marx
/
llama-recipes
1
0
Vork 0
Bestanden Issues 0 Pull-aanvragen 0 Wiki
Boom: 45cf00d9b0
Aftakkingen Labels
llama-recipes
/
recipes
/
responsible_ai
Beto c1be7d802a Updating responsible AI main readme 1 jaar geleden
..
llama_guard bd63fc595a Modifying readmes to match new naming convention 1 jaar geleden
CodeShieldUsageDemo.ipynb 81642c247d Create CodeShieldUsageDemo.ipynb 1 jaar geleden
Purple_Llama_Anyscale.ipynb f53f17138b fix dead links after refactor 1 jaar geleden
Purple_Llama_OctoAI.ipynb f53f17138b fix dead links after refactor 1 jaar geleden
README.md c1be7d802a Updating responsible AI main readme 1 jaar geleden
input_output_guardrails_with_llama.ipynb a404c9249c Notebook to demonstrate using llama and llama-guard together using OctoAI 1 jaar geleden

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.