Update app.py

app.py

@@ -62,6 +62,7 @@ def generate(
         if model in clientList:
             client = InferenceClient(model, token=HF_TOKEN)
             print(f"Choosen model: {model}")
+            break
 
     try:
         stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)