Update model card

README.md

@@ -3,10 +3,12 @@ language:
 - en
 datasets:
 - pubmed
+- chemical patent
+- cooking recipe
 ---
 
 ## ProcBERT
-ProcBERT is a pre-trained language model specifically for procedural text. It was pre-trained on a large-scale procedural corpus (PubMed articles/chemical patents/recipes) containing over 12B tokens and shows great performance on downstream tasks. More details can be found in the following [paper](https://arxiv.org/abs/2109.04711):
+ProcBERT is a pre-trained language model specifically for procedural text. It was pre-trained on a large-scale procedural corpus (PubMed articles/chemical patents/cooking recipes) containing over 12B tokens and shows great performance on downstream tasks. More details can be found in the following [paper](https://arxiv.org/abs/2109.04711):
 
 ```
 @article{Bai2021PretrainOA,
@@ -21,8 +23,8 @@ ProcBERT is a pre-trained language model specifically for procedural text. It wa
 ## Usage
 ```
 from transformers import *
-tokenizer = BertTokenizer.from_pretrained("fbaigt/procbert")
-model = BertForTokenClassification.from_pretrained("fbaigt/procbert")
+tokenizer = AutoTokenizer.from_pretrained("fbaigt/procbert")
+model = AutoModelForTokenClassification.from_pretrained("fbaigt/procbert")
 ```
 
 More usage details can be found [here](https://github.com/bflashcp3f/ProcBERT).