Update app.py

app.py

@@ -54,8 +54,7 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
         conversation.extend([{"role": "user", "content": prompt}, {"role": "assistant", "content": answer}])
     conversation.append({"role": "user", "content": message})
     
-    inputs = tokenizer.apply_chat_template(conversation, tokenize=True, add_generation_prompt=True, return_tensors="pt")
-    input_ids = inputs['input_ids'].to(model.device)
+    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt").to(model.device)
     
     streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)