Upload app.py

app.py

@@ -66,9 +66,12 @@ conversation.append({
 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 {
+gr.Warning((
+f"Trimmed input from conversation as it was longer than "
+f" {
   MAX_INPUT_TOKEN_LENGTH
-} tokens.")
+} tokens."
+))
 input_ids = input_ids.to(model.device)
 
 streamer = TextIteratorStreamer(tokenizer, timeout = 10.0, skip_prompt = True, skip_special_tokens = True)
@@ -107,11 +110,11 @@ chat_interface = gr.ChatInterface(
       value = DEFAULT_MAX_NEW_TOKENS,
     ),
     gr.Slider(
-        label="Temperature",
-        minimum=0,
-        maximum=4.0,
-        step=0.01,
-        value=0,
+      label = "Temperature",
+      minimum = 0,
+      maximum = 4.0,
+      step = 0.01,
+      value = 0,
     ),
     gr.Slider(
       label = "Top-p (nucleus sampling)",