Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

docs: Update README.md #370

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: Update README.md #370

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
8 changes: 7 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -271,11 +271,17 @@ if __name__ == "__main__":
默认情况下，模型以 FP16 精度加载，运行上述代码需要大概 13GB 显存。如果你的 GPU 显存有限，可以尝试以量化方式加载模型，使用方法如下：

```python
model = AutoModel.from_pretrained("THUDM/chatglm2-6b-int4",trust_remote_code=True).cuda()
# 按需修改，目前只支持 4/8 bit 量化
model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).quantize(8).cuda()
```

模型量化会带来一定的性能损失，经过测试，ChatGLM2-6B 在 4-bit 量化下仍然能够进行自然流畅的生成。 量化模型的参数文件也可以从[这里](https://cloud.tsinghua.edu.cn/d/674208019e314311ab5c/)手动下载。

如果你的内存不足，可以直接加载量化后的模型：
```python
model = AutoModel.from_pretrained("THUDM/chatglm2-6b-int4",trust_remote_code=True).cuda()
```

### CPU 部署

如果你没有 GPU 硬件的话，也可以在 CPU 上进行推理，但是推理速度会更慢。使用方法如下（需要大概 32GB 内存）
Expand Down