Spaces:
Paused
Paused
binary-husky
commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -103,24 +103,32 @@ cd chatgpt_academic
|
|
| 103 |
python -m pip install -r requirements.txt
|
| 104 |
|
| 105 |
# (选择II: 如不熟悉python)使用anaconda,步骤也是类似的 (https://www.bilibili.com/video/BV1rc411W7Dr):
|
| 106 |
-
conda create -n gptac_venv python=3.11
|
| 107 |
-
conda activate gptac_venv
|
| 108 |
-
python -m pip install -r requirements.txt
|
| 109 |
```
|
| 110 |
|
| 111 |
-
|
|
|
|
|
|
|
|
|
|
| 112 |
```sh
|
| 113 |
-
#
|
| 114 |
python -m pip install -r request_llm/requirements_chatglm.txt
|
| 115 |
|
| 116 |
-
#
|
| 117 |
python -m pip install -r request_llm/requirements_moss.txt
|
| 118 |
git clone https://github.com/OpenLMLab/MOSS.git request_llm/moss # 注意执行此行代码时,必须处于项目根路径
|
| 119 |
|
| 120 |
-
#
|
| 121 |
AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "newbing", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
|
| 122 |
```
|
| 123 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 124 |
4. 运行
|
| 125 |
```sh
|
| 126 |
python main.py
|
|
|
|
| 103 |
python -m pip install -r requirements.txt
|
| 104 |
|
| 105 |
# (选择II: 如不熟悉python)使用anaconda,步骤也是类似的 (https://www.bilibili.com/video/BV1rc411W7Dr):
|
| 106 |
+
conda create -n gptac_venv python=3.11 # 创建anaconda环境
|
| 107 |
+
conda activate gptac_venv # 激活anaconda环境
|
| 108 |
+
python -m pip install -r requirements.txt # 这个步骤和pip安装一样的步骤
|
| 109 |
```
|
| 110 |
|
| 111 |
+
<details><summary>如果需要支持清华ChatGLM/复旦MOSS作为后端,请点击展开此处</summary>
|
| 112 |
+
<p>
|
| 113 |
+
|
| 114 |
+
【可选步骤】如果需要支持清华ChatGLM/复旦MOSS作为后端,需要额外安装更多依赖(前提条件:熟悉Python + 用过Pytorch + 电脑配置够强):
|
| 115 |
```sh
|
| 116 |
+
# 【可选步骤I】支持清华ChatGLM。清华ChatGLM备注:如果遇到"Call ChatGLM fail 不能正常加载ChatGLM的参数" 错误,参考如下: 1:以上默认安装的为torch+cpu版,使用cuda需要卸载torch重新安装torch+cuda; 2:如因本机配置不够无法加载模型,可以修改request_llm/bridge_chatglm.py中的模型精度, 将 AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 都修改为 AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
|
| 117 |
python -m pip install -r request_llm/requirements_chatglm.txt
|
| 118 |
|
| 119 |
+
# 【可选步骤II】支持复旦MOSS
|
| 120 |
python -m pip install -r request_llm/requirements_moss.txt
|
| 121 |
git clone https://github.com/OpenLMLab/MOSS.git request_llm/moss # 注意执行此行代码时,必须处于项目根路径
|
| 122 |
|
| 123 |
+
# 【可选步骤III】确保config.py配置文件的AVAIL_LLM_MODELS包含了期望的模型,目前支持的全部模型如下(jittorllms系列目前仅支持docker方案):
|
| 124 |
AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "newbing", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
|
| 125 |
```
|
| 126 |
|
| 127 |
+
</p>
|
| 128 |
+
</details>
|
| 129 |
+
|
| 130 |
+
|
| 131 |
+
|
| 132 |
4. 运行
|
| 133 |
```sh
|
| 134 |
python main.py
|