Update README.md

README.md

@@ -33,9 +33,9 @@ Note that this model is primarily aimed at being fine-tuned on tasks that use th
 You can use this model directly with a pipeline for masked language modeling:
 
 ```python
-from transformers import pipeline
-mlm_model = pipeline('fill-mask', model='kiddothe2b/hierarchical-transformer-EC2-mini-1024', trust_remote_code=True)
-mlm_model("Hello I'm a <mask> model.")
+from transformers import AutoTokenizer, AutoModelforForMaskedLM
+tokenizer = AutoTokenizer.from_pretrained("kiddothe2b/hierarchical-transformer-EC2-mini-1024", trust_remote_code=True)
+mlm_model = AutoModelforForMaskedLM(model="kiddothe2b/hierarchical-transformer-EC2-mini-1024", trust_remote_code=True)
 ```
 
 You can also fine-tun it for SequenceClassification, SequentialSentenceClassification, and MultipleChoice down-stream tasks:
@@ -43,7 +43,7 @@ You can also fine-tun it for SequenceClassification, SequentialSentenceClassific
 ```python
 from transformers import AutoTokenizer, AutoModelforSequenceClassification
 tokenizer = AutoTokenizer.from_pretrained("kiddothe2b/hierarchical-transformer-EC2-mini-1024", trust_remote_code=True)
-doc_classifier = AutoModelforSequenceClassification(model='kiddothe2b/hierarchical-transformer-EC2-mini-1024', trust_remote_code=True)
+doc_classifier = AutoModelforSequenceClassification(model="kiddothe2b/hierarchical-transformer-EC2-mini-1024", trust_remote_code=True)
 ```
 
 ## Limitations and bias
@@ -96,7 +96,8 @@ The following hyperparameters were used during training:
 - Tokenizers 0.11.6
 
 
-##Citing
+## Citing
+
 If you use HAT in your research, please cite [An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification](https://arxiv.org/abs/xxx)
 
 ```