Spaces:
Running
Running
binary-husky
commited on
Commit
•
fa395aa
1
Parent(s):
8dded0c
Update README.md
Browse files
README.md
CHANGED
@@ -109,19 +109,19 @@ python -m pip install -r requirements.txt
|
|
109 |
# (II-3)python -m pip install -r requirements.txt
|
110 |
```
|
111 |
|
112 |
-
|
113 |
```sh
|
114 |
-
#
|
115 |
python -m pip install -r request_llm/requirements_chatglm.txt
|
116 |
## 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:
|
117 |
## 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
|
118 |
## 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)
|
119 |
|
120 |
-
#
|
121 |
python -m pip install -r request_llm/requirements_moss.txt
|
122 |
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
|
123 |
|
124 |
-
#
|
125 |
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"]
|
126 |
```
|
127 |
|
|
|
109 |
# (II-3)python -m pip install -r requirements.txt
|
110 |
```
|
111 |
|
112 |
+
【非必要可选步骤】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):
|
113 |
```sh
|
114 |
+
# 【非必要可选步骤I】支持清华ChatGLM
|
115 |
python -m pip install -r request_llm/requirements_chatglm.txt
|
116 |
## 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:
|
117 |
## 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
|
118 |
## 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)
|
119 |
|
120 |
+
# 【非必要可选步骤II】支持复旦MOSS
|
121 |
python -m pip install -r request_llm/requirements_moss.txt
|
122 |
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
|
123 |
|
124 |
+
# 【非必要可选步骤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):
|
125 |
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"]
|
126 |
```
|
127 |
|