phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

fix safety using inference (#99)

Browse source
This commit is contained in:
Xi Yan 2024-09-25 11:30:27 -07:00 • committed by GitHub
parent 5c4f73d52f
commit 82f420c4f0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 4 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/providers/impls/meta_reference/safety/shields/llama_guard.py
View file

@ -18,6 +18,7 @@ from transformers import (
)
from .base import CANNED_RESPONSE_TEXT, OnViolationAction, ShieldBase, ShieldResponse
from llama_models.llama3.api.datatypes import Message, Role
SAFE_RESPONSE = "safe"