Update app.py

app.py

@@ -4,15 +4,18 @@ from huggingface_hub import InferenceClient
 client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
 
 def respond(message, history, max_tokens, temperature, top_p):
-    """Sends user input directly to the model without extra formatting."""
+    """Generates only a short, direct response without extra text."""
     response = client.text_generation(
-        message.strip(),  # ✅ Sends only the question
+        message.strip(),
         max_new_tokens=max_tokens,  
         temperature=temperature,
         top_p=top_p,
     )
 
-    yield response.strip()  # ✅ Removes unnecessary spaces/newlines
+    # ✅ Remove "I am... ", "What do you do?", "Can you help me...?", etc.
+    response = response.strip().split("\n")[0]  # Keep only the first line  
+
+    yield response  
 
 demo = gr.ChatInterface(
     respond,