Update app.py

app.py

@@ -18,7 +18,7 @@ def count_tokens(text):
 def predict(message, history):
 
     formatted_prompt = f"<start_of_turn>user\n{message}<end_of_turn>\n<start_of_turn>model\n"
-    model_inputs = tokenizer(input_text, return_tensors="pt")
+    model_inputs = tokenizer(formatted_prompt, return_tensors="pt")
     
     streamer = TextIteratorStreamer(tokenizer, timeout=120., skip_prompt=True, skip_special_tokens=True)