Inicio Explorar Axuda
Iniciar sesión
radu
/
LLamaRecipes
réplica de https://github.com/facebookresearch/llama-recipes.git
Seguir 1
Destacar 0
Fork 0
Ficheiros Incidencias 0 Wiki
Árbore: 308026aad5
Ramas Etiquetas
LLamaRecipes
/
recipes
/
responsible_ai
Suraj 308026aad5 Adds tentative llamaguard HF model id, eos_token_id for model.generate hai 1 ano
..
llama_guard 308026aad5 Adds tentative llamaguard HF model id, eos_token_id for model.generate hai 1 ano
prompt_guard 0c57646481 Prompt Guard Tutorial hai 1 ano
Purple_Llama_Anyscale.ipynb f53f17138b fix dead links after refactor hai 1 ano
Purple_Llama_OctoAI.ipynb f53f17138b fix dead links after refactor hai 1 ano
README.md 308026aad5 Adds tentative llamaguard HF model id, eos_token_id for model.generate hai 1 ano
code_shield_usage_demo.ipynb 77156c7324 Minor file renames hai 1 ano
input_output_guardrails_with_llama.ipynb a404c9249c Notebook to demonstrate using llama and llama-guard together using OctoAI hai 1 ano

README.md

Meta Llama Guard

Meta Llama Guard models 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.