Update web_demo2.py

当前MAX_BOXES与MAX_TURNS不生效导致单次对话不终止显存不断增加最后显存溢出问题，修改最大对话轮数和最大历史对话数量使其生效，逻辑为历史最大对话框记录轮数达到MAX_BOXES时截断历史对话为最近MAX_TURNS数。

web_demo2.py

@@ -28,6 +28,8 @@ def predict(input, max_length, top_p, temperature, history=None):
 
     with container:
         if len(history) > 0:
+            if len(history)>MAX_BOXES:
+                history = history[-MAX_TURNS:]
             for i, (query, response) in enumerate(history):
                 message(query, avatar_style="big-smile", key=str(i) + "_user")
                 message(response, avatar_style="bottts", key=str(i))
@@ -66,4 +68,4 @@ if 'state' not in st.session_state:
 if st.button("发送", key="predict"):
     with st.spinner("AI正在思考，请稍等........"):
         # text generation
-        st.session_state["state"] = predict(prompt_text, max_length, top_p, temperature, st.session_state["state"])
+        st.session_state["state"] = predict(prompt_text, max_length, top_p, temperature, st.session_state["state"])