Update README.md

README.md

@@ -12,7 +12,7 @@ widget:
 
 ## Model description
 
-This is the set of Chinese T5 Version 1.1 models pre-trained by [UER-py](https://arxiv.org/abs/1909.05658).
+This is the set of Chinese T5 Version 1.1 models pre-trained by [UER-py](https://github.com/dbiir/UER-py/), which is introduced in [this paper](https://arxiv.org/abs/1909.05658).
 
 **Version 1.1**
 
@@ -22,6 +22,8 @@ Chinese T5 Version 1.1 includes the following improvements compared to our Chine
 - Dropout was turned off in pre-training
 - no parameter sharing between embedding and classifier layer
 
+You can download the set of Chinese T5 Version 1.1 models either from the [UER-py Modelzoo page](https://github.com/dbiir/UER-py/wiki/Modelzoo), or via HuggingFace from the links below:
+
 |                   |              Link              |
 | ----------------- | :----------------------------: |
 | **T5-v1_1-Small** | [**L=8/H=512 (Small)**][small] |
@@ -74,7 +76,6 @@ python3 pretrain.py --dataset_path cluecorpussmall_t5-v1_1_seq128_dataset.pt \
                     --embedding word --relative_position_embedding --remove_embedding_layernorm --tgt_embedding word \
                     --encoder transformer --mask fully_visible --layernorm_positioning pre \
                     --feed_forward gated --decoder transformer --target t5
-
 ```
 
 Stage2: