Update app.py

app.py

@@ -57,13 +57,18 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 
 @spaces.GPU
 def stream_chat(message: str, history: list, temperature: float, max_new_tokens: int):
+    print("message:"+ message)
+    print("history:"+ history)
     conversation = []
     for prompt, answer in history:
         conversation.extend([{"role": "user", "content": prompt}, {"role": "assistant", "content": answer}])
 
     conversation.append({"role": "user", "content": message})
 
+    print("conversation:"+ conversation)
+    
     input_ids = tokenizer.apply_chat_template(conversation, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
+    
     prompt_padded_len = len(input_ids[0])
 
     gen_tokens= model.generate(