Matthew Farrellee
|
ef26259209
|
feat: add llama guard 4 model (#2579)
add support for Llama Guard 4 model to the llama_guard safety provider
test with -
0. NVIDIA_API_KEY=... llama stack build --image-type conda --image-name
env-nvidia --providers
inference=remote::nvidia,safety=inline::llama-guard --run
1. llama-stack-client models register meta-llama/Llama-Guard-4-12B
--provider-model-id meta/llama-guard-4-12b
2. pytest tests/integration/safety/test_llama_guard.py
Co-authored-by: raghotham <rsm@meta.com>
|
2025-07-03 22:29:04 -07:00 |
|