s-JoL commited on
Commit
7a4db28
1 Parent(s): 99fe8c0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -48,6 +48,12 @@ The specific release versions and download links are listed in the table below:
48
  | 13B | [Baichuan2-13B-Base](https://huggingface.co/baichuan-inc/Baichuan2-13B-Base) | [Baichuan2-13B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat) | [Baichuan2-13B-Chat-4bits](https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat-4bits) |
49
 
50
  # <span id="Start">快速开始/Quick Start</span>
 
 
 
 
 
 
51
  ```python
52
  import torch
53
  from transformers import AutoModelForCausalLM, AutoTokenizer
 
48
  | 13B | [Baichuan2-13B-Base](https://huggingface.co/baichuan-inc/Baichuan2-13B-Base) | [Baichuan2-13B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat) | [Baichuan2-13B-Chat-4bits](https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat-4bits) |
49
 
50
  # <span id="Start">快速开始/Quick Start</span>
51
+
52
+ 在Baichuan2系列模型中,我们为了加快推理速度使用了Pytorch2.0加入的新功能F.scaled_dot_product_attention,因此模型需要在Pytorch2.0环境下运行。
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
  ```python
58
  import torch
59
  from transformers import AutoModelForCausalLM, AutoTokenizer