update to smaller model for poc

app.py

@@ -4,7 +4,9 @@ from huggingface_hub import InferenceClient
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("mistralai/Mistral-Large-Instruct-2407")
+# requires space hardware update to use large models (TODO)
+# client = InferenceClient("mistralai/Mistral-Large-Instruct-2407")
+client = InferenceClient("EleutherAI/gpt-neo-125M")
 
 
 def respond(