phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-07 12:47:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

set temp=0, re-record

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-30 11:19:59 -04:00
parent c24a2d8929
commit 958336cc98
72 changed files with 86 additions and 18070 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/inline/safety/llama_guard/llama_guard.py
View file

@ -290,12 +290,11 @@ class LlamaGuardShield:
else:
shield_input_message = self.build_text_shield_input(messages)
# TODO: llama-stack inference protocol has issues with non-streaming inference code
response = await self.inference_api.openai_chat_completion(
model=self.model,
messages=[shield_input_message],
stream=False,
temperature=0.0001, # TODO: find a better way
temperature=0.0, # default is 1, which is too high for safety
)
content = response.choices[0].message.content
content = content.strip()