[feat] update model install method

README.md

@@ -236,12 +236,37 @@ pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple
 
 ### 2.下载模型
 
-到项目根目录
+到项目根目录：
+
+```bash
+cd minimind
+```
+
+方法一：使用 Git + Git LFS（需要预装 [Git LFS](https://git-lfs.com/)）
 
 ```bash
 git clone https://huggingface.co/jingyaogong/MiniMind2 # or https://www.modelscope.cn/models/gongjy/MiniMind2
 ```
 
+方法二：使用 hf CLI
+
+```bash
+hf download jingyaogong/MiniMind2 --local-dir ./MiniMind2
+```
+
+方法三：使用 hf CLI + 更换下载源（大陆推荐）
+
+```bash
+export HF_ENDPOINT=https://hf-mirror.com
+hf download jingyaogong/MiniMind2 --local-dir ./MiniMind2
+```
+
+方法四：使用 modelscope CLI（大陆推荐）
+
+```bash
+modelscope download --model gongjy/MiniMind2 --local_dir ./MiniMind2
+```
+
 ### （可选）命令行问答
 
 ```bash
@@ -1911,4 +1936,3 @@ If you find MiniMind helpful in your research or work, please cite:
 
 This repository is licensed under the [Apache-2.0 License](LICENSE).
 
-

README_en.md

@@ -243,10 +243,35 @@ pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple
 
 Go to the project root directory
 
+```bash
+cd minimind
+```
+
+Method 1: Using Git + Git LFS (Requires pre-installed [Git LFS](https://git-lfs.com/))
+
 ```bash
 git clone https://huggingface.co/jingyaogong/MiniMind2 # or https://www.modelscope.cn/models/gongjy/MiniMind2
 ```
 
+Method 2: Using hf CLI
+
+```bash
+hf download jingyaogong/MiniMind2 --local-dir ./MiniMind2
+```
+
+Method 3: Using hf CLI + Changing download source (Recommended in Mainland China)
+
+```bash
+export HF_ENDPOINT=https://hf-mirror.com
+hf download jingyaogong/MiniMind2 --local-dir ./MiniMind2
+```
+
+Method 4: Using modelscope CLI (Recommended in Mainland China)
+
+```bash
+modelscope download --model gongjy/MiniMind2 --local_dir ./MiniMind2
+```
+
 ### (Optional) Command Line Q&A
 
 ```bash

requirements.txt

@@ -2,10 +2,12 @@ datasets==3.6.0
 datasketch==1.6.4
 Flask==3.0.3
 Flask_Cors==4.0.0
+huggingface-hub==0.36.0
 jieba==0.42.1
 jsonlines==4.0.0
 marshmallow==3.22.0
 matplotlib==3.10.0
+modelscope==1.31.0
 ngrok==1.4.0
 nltk==3.8
 numpy==1.26.4