Update README.md

README.md

@@ -87,20 +87,6 @@ For MMLU, we adopt the [evaluation tools](https://github.com/hendrycks/test) pro
 
 ## 使用方法
 
-### 环境安装
-
-1. 下载本仓库：
-
-```shell
-git clone https://github.com/xverse-ai/XVERSE-MoE-A4.2B
-cd XVERSE-MoE-A4.2B
-```
-
-2. 使用 pip 安装依赖：
-
-```shell
-pip install -r requirements.txt
-```
 ### Transformers 加载方式
 
 可通过以下代码加载 XVERSE-MoE-A4.2B 模型来进行推理：
@@ -117,31 +103,9 @@ generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer
 print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))
 ```
 
-### 网页 Demo
-
-可通过以下代码启动一个web server，在浏览器输入访问地址后，可使用 XVERSE-MoE-A4.2B 模型进行推理：
-
-```shell
-python text_generation_demo.py --port='port' --model_path='/path/to/model/' --tokenizer_path='/path/to/tokenizer/'
-```
 
 ## Usage
 
-### Environment Setup
-
-1. Clone this repository:
-
-```shell
-git clone https://github.com/xverse-ai/XVERSE-MoE-A4.2B
-cd XVERSE-MoE-A4.2B
-```
-
-2. Install the dependencies using pip:
-
-```shell
-pip install -r requirements.txt
-```
-
 ### Loading with Transformers
 
 The XVERSE-MoE-A4.2B model can be loaded for inference using the following code:
@@ -158,13 +122,6 @@ generated_ids = model.generate(inputs, max_new_tokens=64, eos_token_id=tokenizer
 print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))
 ```
 
-### Web Demo
-
-The following code can be used to start a web server. By entering the access address in the browser, you can perform inference with the XVERSE-MoE-A4.2B model:
-
-```shell
-python chat_demo.py --port='port' --model_path='/path/to/model/' --tokenizer_path='/path/to/tokenizer/'
-```
 
 ## 局限性与免责申明
 
@@ -174,7 +131,7 @@ XVERSE-MoE-A4.2B 与其他所有 LLM 一样，在某些情况下可能会产生
 
 ## 模型开源协议
 
-使用本仓库的源码需要遵循 [Apache-2.0](LICENSE) 开源协议，使用 XVERSE-MoE-A4.2B 的模型权重则需要遵循[模型许可协议](MODEL_LICENSE.pdf)。
+使用本仓库的源码需要遵循 [Apache-2.0](https://github.com/xverse-ai/XVERSE-MoE-A4.2B/blob/main/LICENSE) 开源协议，使用 XVERSE-MoE-A4.2B 的模型权重则需要遵循[模型许可协议](https://github.com/xverse-ai/XVERSE-MoE-A4.2B/blob/main/MODEL_LICENSE.pdf)。
 
 XVERSE-MoE-A4.2B 模型权重对学术研究**完全开放**，并且支持**免费商用**。如需申请商业许可证，请填写【[申请表](https://chat.xverse.cn/home/business.html)】，如有其他问题或合作，请联系 <opensource@xverse.cn>。
 
@@ -186,6 +143,6 @@ We strongly warn against the use of the XVERSE-MoE-A4.2B model for producing or
 
 ## Open Source License
 
-The use of the source code in this repository must follow the [Apache-2.0](LICENSE) open-source license, while the use of the model weights of XVERSE-MoE-A4.2B needs to adhere to the [Model License Agreement](MODEL_LICENSE.pdf).
+The use of the source code in this repository must follow the [Apache-2.0](https://github.com/xverse-ai/XVERSE-MoE-A4.2B/blob/main/LICENSE) open-source license, while the use of the model weights of XVERSE-MoE-A4.2B needs to adhere to the [Model License Agreement](https://github.com/xverse-ai/XVERSE-MoE-A4.2B/blob/main/MODEL_LICENSE.pdf).
 
 The XVERSE-MoE-A4.2B model weights are **fully open** to academic research and support **free commercial use**.  To apply for a commercial license, please fill in the [application form](https://chat.xverse.cn/home/business.html). For other questions or collaborations, please contact <opensource@xverse.cn>.