Sākums Izpētīt Palīdzība
Reģistrēties Pierakstīties
marx
/
llama-recipes
1
0
Atdalīts 0
Faili Problēmas 0 Izmaiņu pieprasījumi 0 Vikivietne
Atzars: main
Atzari Tagi
llama-recipes
/
recipes
/
responsible_ai
Beto c1be7d802a Updating responsible AI main readme 7 mēneši atpakaļ
..
llama_guard bd63fc595a Modifying readmes to match new naming convention 7 mēneši atpakaļ
CodeShieldUsageDemo.ipynb 81642c247d Create CodeShieldUsageDemo.ipynb 7 mēneši atpakaļ
Purple_Llama_Anyscale.ipynb f53f17138b fix dead links after refactor 8 mēneši atpakaļ
Purple_Llama_OctoAI.ipynb f53f17138b fix dead links after refactor 8 mēneši atpakaļ
README.md c1be7d802a Updating responsible AI main readme 7 mēneši atpakaļ
input_output_guardrails_with_llama.ipynb a404c9249c Notebook to demonstrate using llama and llama-guard together using OctoAI 8 mēneši atpakaļ

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.