Update README.md

README.md

@@ -2,6 +2,31 @@
 language: en
 ---
 # CPT
+
+## Requirements
+
+First, install PyTorch by following the instructions from [the official website](https://pytorch.org). To faithfully reproduce our results, please use the correct `1.7.0` version corresponding to your platforms/CUDA versions. PyTorch version higher than `1.7.0` should also work. For example, if you use Linux and **CUDA11** ([how to check CUDA version](https://varhowto.com/check-cuda-version/)), install PyTorch by the following command,
+
+```bash
+pip install torch==1.7.0+cu110 -f https://download.pytorch.org/whl/torch_stable.html
+```
+
+If you instead use **CUDA** `<11` or **CPU**, install PyTorch by the following command,
+
+```bash
+pip install torch==1.7.0
+```
+
+Then run the following script to install the remaining dependencies,
+
+```bash
+pip install -r requirements.txt
+```
+
+**Attention**: Our model is based on `transformers==4.11.3` and `adapter-transformers==2.2.0`. Using them from other versions may cause some unexpected bugs.
+
+## Use CPT with Huggingface
+
 You can easily import our continually post-trained model with HuggingFace's `transformers`:
 
 ```python
@@ -34,6 +59,4 @@ Note: The post-trained weights you load contain un-trained classification heads.
 
 |                 | Restaurant    | AI            | ACL           | AGNews        | Avg.          |
 | --------------- | ------------- | ------------- | ------------- | ------------- | ------------- |
-| UIC-Liu-Lab/CPT | 53.90 / 75.13 | 30.42 / 30.89 | 37.56 / 38.53 | 63.77 / 65.79 | 46.41 / 52.59 |
-
-## 
+| UIC-Liu-Lab/CPT | 53.90 / 75.13 | 30.42 / 30.89 | 37.56 / 38.53 | 63.77 / 65.79 | 46.41 / 52.59 |