From aa9a9f18beff408ed75df2ac9b3eb29cb96ba0f1 Mon Sep 17 00:00:00 2001 From: Aidan Do Date: Sat, 14 Dec 2024 16:35:24 +1100 Subject: [PATCH] Move model_id above so warning actually works --- llama_stack/providers/remote/inference/groq/groq.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/llama_stack/providers/remote/inference/groq/groq.py b/llama_stack/providers/remote/inference/groq/groq.py index ccd1fc0c5..3576478ff 100644 --- a/llama_stack/providers/remote/inference/groq/groq.py +++ b/llama_stack/providers/remote/inference/groq/groq.py @@ -104,7 +104,7 @@ class GroqInferenceAdapter(Inference, ModelRegistryHelper): ) -> Union[ ChatCompletionResponse, AsyncIterator[ChatCompletionResponseStreamChunk] ]: - +model_id = self.get_provider_model_id(model_id) if model_id == "llama-3.2-3b-preview": warnings.warn( "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." ) - model_id = self.get_provider_model_id(model_id) request = convert_chat_completion_request( request=ChatCompletionRequest( model=model_id,