Halaman utama Jelajahi Bantuan
Masuk
radu
/
LLamaRecipes
cermin dari https://github.com/facebookresearch/llama-recipes.git
Liatin 1
Bintangi 0
Fork 0
Berkas Masalah 0 Wiki
Cabang: fsdp-qlora
Ranting Tag
LLamaRecipes
/
recipes
/
responsible_ai
Matthias Reso d9edc0ca08 Update docs 9 bulan lalu
..
llama_guard d9edc0ca08 Update docs 9 bulan lalu
Purple_Llama_Anyscale.ipynb f53f17138b fix dead links after refactor 1 tahun lalu
Purple_Llama_OctoAI.ipynb f53f17138b fix dead links after refactor 1 tahun lalu
README.md 28eea83a52 Spellcheck error fixed 10 bulan lalu
code_shield_usage_demo.ipynb 77156c7324 Minor file renames 10 bulan lalu
input_output_guardrails_with_llama.ipynb a404c9249c Notebook to demonstrate using llama and llama-guard together using OctoAI 1 tahun lalu

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.