Update app.py

app.py

@@ -5,13 +5,17 @@ from huggingface_hub import InferenceClient
 client = InferenceClient("NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO")
 
 def generate_response(prompt, max_length=512, temperature=0.7):
-    """Generate a response from the model."""
+    """Generate a response from the model and check metadata."""
     response = client.text_generation(
         prompt,
         max_new_tokens=max_length,
         temperature=temperature,
+        details=True  # This may provide extra model info
     )
-    return response
+    print(f"Response Metadata: {response}")  # Check if model details are in the response
+    return response["generated_text"] if isinstance(response, dict) else response
+
+print(f"Using model: {client.model_id}")
 
 # Define the Gradio interface
 iface = gr.Interface(