Update app.py

app.py

@@ -25,7 +25,6 @@ def generate(
     temperature: float = 0.7,
     top_p: float = 1.0,
     repetition_penalty: float = 1.1,
-    input_button: bool = False
 ) -> Iterator[str]:
     conversation = []
     if system_prompt:
@@ -37,7 +36,7 @@ def generate(
     input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
     if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
         input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
-        gr.Warning(f"Trimmed input from conversation as it was longer than {str(MAX_INPUT_TOKEN_LENGTH)} tokens.")
+        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
     input_ids = input_ids.to(model.device)
 
     streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
@@ -92,7 +91,7 @@ chat_interface = gr.Interface(
             step=0.05,
             value=1.1,
         ),
-        gr.Button("Generate Response")
+        "generate"  # This is a placeholder for the button
     ],
     outputs=gr.Textbox(label="Chat Output", lines=10),
     title="🦣MAmmoTH2",