diff --git a/README.md b/README.md
index c8e065e..258069a 100644
--- a/README.md
+++ b/README.md
@@ -68,7 +68,7 @@ docker run -d --gpus all -p 80:8501 registry.cn-beijing.aliyuncs.com/chatchat/ch
 + chatglm2-6b & LLaMA-7B  最低显存要求: 7GB   推荐显卡: RTX 3060, RTX 2060
 + LLaMA-13B 最低显存要求: 11GB  推荐显卡: RTX 2060 12GB, RTX3060 12GB, RTX3080, RTXA2000 
 + Qwen-14B-Chat 最低显存要求: 13GB 推荐显卡: RTX 3090
-+ LLaMA-30B 最低显存要求: 22GB  推荐显卡：RTX A5000,RTX 3090,RTX 4090,RTX 6000,Tesla V100,RTX Tesla P40 
++ LLaMA-30B 最低显存要求: 22GB  推荐显卡：RTX A5000,RTX 3090,RTX 4090,RTX 6000,Tesla V100,RTX Tesla P40
 + LLaMA-65B 最低显存要求: 40GB  推荐显卡：A100,A40,A6000
 
 如果是int8 则显存x1.5 fp16 x2.5的要求
diff --git a/README_en.md b/README_en.md
index c7771ff..8a20916 100644
--- a/README_en.md
+++ b/README_en.md
@@ -67,9 +67,10 @@ If you want to run the native model (int4 version) on the GPU without problems,
 + chatglm2-6b & LLaMA-7B Minimum RAM requirement: 7GB Recommended graphics cards: RTX 3060, RTX 2060
 + LLaMA-13B Minimum graphics memory requirement: 11GB Recommended cards: RTX 2060 12GB, RTX3060 12GB, RTX3080, RTXA2000 
 + Qwen-14B-Chat Minimum memory requirement: 13GB Recommended graphics card: RTX 3090
-+ LLaMA-30B Minimum Memory Requirement: 22GB Recommended Cards: RTX A5000,RTX 3090,RTX 4090,RTX 6000,Tesla V100,RTX Tesla P40 
++ LLaMA-30B Minimum Memory Requirement: 22GB Recommended Cards: RTX A5000,RTX 3090,RTX 4090,RTX 6000,Tesla V100,RTX Tesla P40
 + Minimum memory requirement for LLaMA-65B: 40GB Recommended cards: A100,A40,A6000
 
+
 If int8 then memory x1.5 fp16 x2.5 requirement.
 For example: using fp16 to reason about the Qwen-7B-Chat model requires 16GB of video memory.
 
diff --git a/configs/model_config.py.example b/configs/model_config.py.example
index 464e01b..59a1f7e 100644
--- a/configs/model_config.py.example
+++ b/configs/model_config.py.example
@@ -92,6 +92,7 @@ MODEL_PATH = {
 # 选用的 Embedding 名称
 EMBEDDING_MODEL = "m3e-base" # 可以尝试最新的嵌入式sota模型：piccolo-large-zh
 
+
 # Embedding 模型运行设备。设为"auto"会自动检测，也可手动设定为"cuda","mps","cpu"其中之一。
 EMBEDDING_DEVICE = "auto"
 
diff --git a/server/agent/callbacks.py b/server/agent/callbacks.py
index 394d227..3901f7e 100644
--- a/server/agent/callbacks.py
+++ b/server/agent/callbacks.py
@@ -1,3 +1,4 @@
+from __future__ import annotations
 from uuid import UUID
 from langchain.callbacks import AsyncIteratorCallbackHandler
 import json
diff --git a/server/agent/custom_template.py b/server/agent/custom_template.py
index 25697a6..aa4aa11 100644
--- a/server/agent/custom_template.py
+++ b/server/agent/custom_template.py
@@ -1,3 +1,4 @@
+from __future__ import annotations
 from langchain.agents import Tool, AgentOutputParser
 from langchain.prompts import StringPromptTemplate
 from typing import List, Union