ChloeAuYeung commited on
Commit
5605492
1 Parent(s): ddaa64a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -45
README.md CHANGED
@@ -87,20 +87,6 @@ For MMLU, we adopt the [evaluation tools](https://github.com/hendrycks/test) pro
87
 
88
  ## 使用方法
89
 
90
- ### 环境安装
91
-
92
- 1. 下载本仓库:
93
-
94
- ```shell
95
- git clone https://github.com/xverse-ai/XVERSE-MoE-A4.2B
96
- cd XVERSE-MoE-A4.2B
97
- ```
98
-
99
- 2. 使用 pip 安装依赖:
100
-
101
- ```shell
102
- pip install -r requirements.txt
103
- ```
104
  ### Transformers 加载方式
105
 
106
  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
117
  print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))
118
  ```
119
 
120
- ### 网页 Demo
121
-
122
- 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:
123
-
124
- ```shell
125
- python text_generation_demo.py --port='port' --model_path='/path/to/model/' --tokenizer_path='/path/to/tokenizer/'
126
- ```
127
 
128
  ## Usage
129
 
130
- ### Environment Setup
131
-
132
- 1. Clone this repository:
133
-
134
- ```shell
135
- git clone https://github.com/xverse-ai/XVERSE-MoE-A4.2B
136
- cd XVERSE-MoE-A4.2B
137
- ```
138
-
139
- 2. Install the dependencies using pip:
140
-
141
- ```shell
142
- pip install -r requirements.txt
143
- ```
144
-
145
  ### Loading with Transformers
146
 
147
  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
158
  print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))
159
  ```
160
 
161
- ### Web Demo
162
-
163
- 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:
164
-
165
- ```shell
166
- python chat_demo.py --port='port' --model_path='/path/to/model/' --tokenizer_path='/path/to/tokenizer/'
167
- ```
168
 
169
  ## 局限性与免责申明
170
 
@@ -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
174
 
175
  ## 模型开源协议
176
 
177
- 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)。
178
 
179
  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>。
180
 
@@ -186,6 +143,6 @@ We strongly warn against the use of the XVERSE-MoE-A4.2B model for producing or
186
 
187
  ## Open Source License
188
 
189
- 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).
190
 
191
  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>.
 
87
 
88
  ## 使用方法
89
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90
  ### Transformers 加载方式
91
 
92
  可通过以下代码加载 XVERSE-MoE-A4.2B 模型来进行推理:
 
103
  print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))
104
  ```
105
 
 
 
 
 
 
 
 
106
 
107
  ## Usage
108
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
109
  ### Loading with Transformers
110
 
111
  The XVERSE-MoE-A4.2B model can be loaded for inference using the following code:
 
122
  print(tokenizer.batch_decode(generated_ids, skip_special_tokens=True))
123
  ```
124
 
 
 
 
 
 
 
 
125
 
126
  ## 局限性与免责申明
127
 
 
131
 
132
  ## 模型开源协议
133
 
134
+ 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)。
135
 
136
  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>。
137
 
 
143
 
144
  ## Open Source License
145
 
146
+ 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).
147
 
148
  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>.