phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-12 13:00:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update groq.py

Browse source
This commit is contained in:
Yuan Tang 2025-02-13 11:09:40 -05:00 • committed by GitHub
parent a8cc981cb4
commit 1f52582aac
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 3 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/remote/inference/groq/groq.py
View file

@ -65,7 +65,7 @@ _MODEL_ALIASES = [
# TODO(aidand): Replace this with a stable model once Groq supports it # TODO(aidand): Replace this with a stable model once Groq supports it
build_model_alias( build_model_alias(
"llama-3.2-3b-preview", "llama-3.2-3b-preview",
CoreModelId.llama3_2_3b.value, CoreModelId.llama3_2_3b_instruct.value,
), ),
] ]
@ -105,9 +105,10 @@ class GroqInferenceAdapter(Inference, ModelRegistryHelper, NeedsRequestProviderD
model_id = self.get_provider_model_id(model_id) 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. " "Groq only contains a preview version for llama-3.2-3b-instruct. "
"Preview models aren't recommended for production use. " "Preview models aren't recommended for production use. "
"They can be discontinued on short notice." "They can be discontinued on short notice."
"More details: https://console.groq.com/docs/models"
) )
request = convert_chat_completion_request( request = convert_chat_completion_request(