diff --git a/README.md b/README.md
index 39b091f..859a4c4 100644
--- a/README.md
+++ b/README.md
@@ -36,14 +36,16 @@ https://github.com/polarwinkel/mdtex2html
 自定义快捷键 | 支持自定义快捷键
 配置代理服务器 | 支持配置代理服务器
 模块化设计 | 支持自定义高阶的实验性功能
-自我程序剖析 | [实验性功能] 一键读懂本项目的源代码
-程序剖析 | [实验性功能] 一键可以剖析其他Python/C++项目
-读论文 | [实验性功能] 一键解读latex论文全文并生成摘要
-批量注释生成 | [实验性功能] 一键批量生成函数注释
-chat分析报告生成 | [实验性功能] 运行后自动生成总结汇报
+自我程序剖析 | [函数插件] 一键读懂本项目的源代码
+程序剖析 | [函数插件] 一键可以剖析其他Python/C++等项目
+读论文 | [函数插件] 一键解读latex论文全文并生成摘要
+arxiv小助手 | [函数插件] 输入url一键翻译摘要+下载论文
+批量注释生成 | [函数插件] 一键批量生成函数注释
+chat分析报告生成 | [函数插件] 运行后自动生成总结汇报
 公式显示 | 可以同时显示公式的tex形式和渲染形式
 图片显示 | 可以在markdown中显示图片
 支持GPT输出的markdown表格 | 可以输出支持GPT的markdown表格
+本地大语言模型接口 | 借助[TGUI](https://github.com/oobabooga/text-generation-webui)接入galactica等本地语言模型
 …… | ……
 
 </div>
diff --git a/main.py b/main.py
index 533e590..0016d9c 100644
--- a/main.py
+++ b/main.py
@@ -11,8 +11,9 @@ proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT =
 PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
 if not AUTHENTICATION: AUTHENTICATION = None
 
+title = "ChatGPT 学术优化" if LLM_MODEL.startswith('gpt') else "ChatGPT / LLM 学术优化"
 initial_prompt = "Serve me as a writing and programming assistant."
-title_html = """<h1 align="center">ChatGPT 学术优化</h1>"""
+title_html = f"<h1 align=\"center\">{title}</h1>"
 
 # 问询记录, python 版本建议3.9+（越新越好）
 import logging
@@ -140,5 +141,5 @@ def auto_opentab_delay():
     threading.Thread(target=open, name="open-browser", daemon=True).start()
 
 auto_opentab_delay()
-demo.title = "ChatGPT 学术优化"
+demo.title = title
 demo.queue(concurrency_count=CONCURRENT_COUNT).launch(server_name="0.0.0.0", share=True, server_port=PORT, auth=AUTHENTICATION)
diff --git a/request_llm/bridge_tgui.py b/request_llm/bridge_tgui.py
index 20a6352..d7cbe10 100644
--- a/request_llm/bridge_tgui.py
+++ b/request_llm/bridge_tgui.py
@@ -24,9 +24,9 @@ def random_hash():
     letters = string.ascii_lowercase + string.digits
     return ''.join(random.choice(letters) for i in range(9))
 
-async def run(context):
+async def run(context, max_token=512):
     params = {
-        'max_new_tokens': 512,
+        'max_new_tokens': max_token,
         'do_sample': True,
         'temperature': 0.5,
         'top_p': 0.9,
@@ -116,12 +116,15 @@ def predict_tgui(inputs, top_p, temperature, chatbot=[], history=[], system_prom
     prompt = inputs
     tgui_say = ""
 
-    mutable = [""]
+    mutable = ["", time.time()]
     def run_coorotine(mutable):
         async def get_result(mutable):
             async for response in run(prompt):
                 print(response[len(mutable[0]):])
                 mutable[0] = response
+                if (time.time() - mutable[1]) > 3: 
+                    print('exit when no listener')
+                    break
         asyncio.run(get_result(mutable))
 
     thread_listen = threading.Thread(target=run_coorotine, args=(mutable,), daemon=True)
@@ -129,6 +132,7 @@ def predict_tgui(inputs, top_p, temperature, chatbot=[], history=[], system_prom
 
     while thread_listen.is_alive():
         time.sleep(1)
+        mutable[1] = time.time()
         # Print intermediate steps
         if tgui_say != mutable[0]:
             tgui_say = mutable[0]
@@ -147,12 +151,17 @@ def predict_tgui_no_ui(inputs, top_p, temperature, history=[], sys_prompt=""):
     mutable = ["", time.time()]
     def run_coorotine(mutable):
         async def get_result(mutable):
-            async for response in run(prompt):
+            async for response in run(prompt, max_token=20):
                 print(response[len(mutable[0]):])
                 mutable[0] = response
+                if (time.time() - mutable[1]) > 3: 
+                    print('exit when no listener')
+                    break
         asyncio.run(get_result(mutable))
     thread_listen = threading.Thread(target=run_coorotine, args=(mutable,))
     thread_listen.start()
-    thread_listen.join()
+    while thread_listen.is_alive():
+        time.sleep(1)
+        mutable[1] = time.time()
     tgui_say = mutable[0]
     return tgui_say