kailinjiang/punkt

## 🛠️ Requirements and Installation

```text
# clone ICE
git clone https://github.com/Yofuria/ICE.git
cd ICE

# create conda env
conda create -n ICE python=3.10
conda activate ICE

# install package
pip install -r requirements.txt
```

In **lines 32 and 33** of **` examples/run_knowedit_llama2.py`**, you need to download the **` punkt `** package.

- If your Internet **speed is fast** enough, you can **run the code directly** from the command line.

```text
if __name__ == "__main__":
# If you have a slow Internet connection and can't download nltk quickly, comment these two lines and use the second method of Requirements and Installation in README.md
import nltk
nltk.download('punkt')
```

- If your Internet **speed is slow**, **comment lines 32 and 33** and download punkt manually. And place it in the ICE environment directory you created, create a **nltk_data/tokenizers** folder, and **unpack punkt** into this directory.

<div align="center"> <img src="punkt.png" width="650px"> </div>

## 🛠️ 环境要求与安装

text
# 克隆ICE仓库
git clone https://github.com/Yofuria/ICE.git
cd ICE

# 创建Conda虚拟环境
conda create -n ICE python=3.10
conda activate ICE

# 安装依赖包
pip install -r requirements.txt

在`examples/run_knowedit_llama2.py`的第32行与第33行中，需下载`punkt`工具包。

- 若网络速度充足，可直接通过命令行运行下述代码：
python
if __name__ == "__main__":
# 若网络连接较慢无法快速下载自然语言工具包（Natural Language Toolkit，NLTK）资源，请注释以下两行代码，并采用README文档中「环境要求与安装」的第二种方案
import nltk
nltk.download('punkt')

- 若网络速度较慢，请注释第32行与第33行代码，并手动下载`punkt`包。将其放置于你所创建的ICE虚拟环境目录中，新建`nltk_data/tokenizers`文件夹，并将`punkt`解压至该目录下。

<div align="center"> <img src="punkt.png" width="650px"> </div>