phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 01:03:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Move model_id above so warning actually works

Browse source
This commit is contained in:
Aidan Do 2024-12-14 16:35:24 +11:00 • committed by GitHub
parent 3587f0894d
commit aa9a9f18be
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/remote/inference/groq/groq.py
View file

@ -104,7 +104,7 @@ class GroqInferenceAdapter(Inference, ModelRegistryHelper):
) -> Union[ ) -> Union[
ChatCompletionResponse, AsyncIterator[ChatCompletionResponseStreamChunk] ChatCompletionResponse, AsyncIterator[ChatCompletionResponseStreamChunk]
]: ]:
model_id = self.get_provider_model_id(model_id)
if model_id == "llama-3.2-3b-preview": if model_id == "llama-3.2-3b-preview":
warnings.warn( warnings.warn(
"Groq only contains a preview version for llama-3.2-3b-instruct. " "Groq only contains a preview version for llama-3.2-3b-instruct. "
@ -112,7 +112,6 @@ class GroqInferenceAdapter(Inference, ModelRegistryHelper):
"They can be discontinued on short notice." "They can be discontinued on short notice."
) )
model_id = self.get_provider_model_id(model_id)
request = convert_chat_completion_request( request = convert_chat_completion_request(
request=ChatCompletionRequest( request=ChatCompletionRequest(
model=model_id, model=model_id,