github
/
ChatGLM2-6B
mirror of https://github.com/THUDM/ChatGLM2-6B
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge 5969eeaf06 into cb8e8b43c0

pull/147/merge
limix 2024-12-15 17:40:37 +00:00 committed by GitHub
parent cb8e8b43c0 5969eeaf06
commit 30bd062117
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
README.md
View File

@ -211,6 +211,13 @@ pip install -r requirements.txt
如果这些方法无法帮助你入睡,你可以考虑咨询医生或睡眠专家,寻求进一步的建议。
```
* 针对macbook pro m1max 电脑，请使用以下命令 ``AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True, device='cuda')``替换为下面的语句
```python
model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().to('mps')
```
#### 从本地加载模型
以上代码会由 `transformers` 自动下载模型实现和参数。完整的模型实现在 [Hugging Face Hub](https://huggingface.co/THUDM/chatglm2-6b)。如果你的网络环境较差，下载模型参数可能会花费较长时间甚至失败。此时可以先将模型下载到本地，然后从本地加载。