update zhou

app.py

@@ -78,13 +78,17 @@ def chat_llama3_8b(message: str,
     for user, assistant in history:
         history_messages.extend(assistant)
     
-    conversation = [
-        message,          # 当前消息
-        history_messages  # 历史消息数组
-    ]
-
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
+    # conversation = [
+    #     message,          # 当前消息
+    #     history_messages  # 历史消息数组
+    # ]
+    conversation = ""
+    for user, assistant in history:
+        conversation += f"User: {user}\nAssistant: {assistant}<|endoftext|>\n"
+    conversation += f"User: {message}\nAssistant: "
     
+    tokenizer.chat_template = "User:{query}\nAssistant:{response}<|endoftext|>"
+    input_ids = tokenizer.encode(conversation, return_tensors="pt").to(model.device)
     streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
 
     generate_kwargs = dict(