Update README.md
Browse files
README.md
CHANGED
|
@@ -53,9 +53,9 @@ The specific release versions and download links are listed in the table below:
|
|
| 53 |
|
| 54 |
In the Baichuan 2 series models, we have utilized the new feature `F.scaled_dot_product_attention` introduced in PyTorch 2.0 to accelerate inference speed. Therefore, the model needs to be run in a PyTorch 2.0 environment.
|
| 55 |
|
| 56 |
-
|
| 57 |
|
| 58 |
-
We have uploaded the checkpoints during training to this project. You can load checkpoints from different steps by specifying the revision
|
| 59 |
|
| 60 |
```python
|
| 61 |
import torch
|
|
|
|
| 53 |
|
| 54 |
In the Baichuan 2 series models, we have utilized the new feature `F.scaled_dot_product_attention` introduced in PyTorch 2.0 to accelerate inference speed. Therefore, the model needs to be run in a PyTorch 2.0 environment.
|
| 55 |
|
| 56 |
+
**我们将训练中的Checkpoints上传到了本项目中，可以通过指定revision来加载不同step的Checkpoint。**
|
| 57 |
|
| 58 |
+
**We have uploaded the checkpoints during training to this project. You can load checkpoints from different steps by specifying the revision.**
|
| 59 |
|
| 60 |
```python
|
| 61 |
import torch
|