Update README.md

README.md

@@ -19,9 +19,10 @@ In total, our dataset contains around 5.4 million Indian legal documents (all in
 The raw text corpus size is around 27 GB.
 
 ### Training Objective
-This model is initialized with the [LEGAL-BERT-SC model](https://huggingface.co/nlpaueb/legal-bert-base-uncased) from the paper [LEGAL-BERT: The Muppets straight out of Law School](https://aclanthology.org/2020.findings-emnlp.261/), and trained for an additional 300K steps on our data on the MLM and NSP objective.
+This model is initialized with the [LEGAL-BERT-SC model](https://huggingface.co/nlpaueb/legal-bert-base-uncased) from the paper [LEGAL-BERT: The Muppets straight out of Law School](https://aclanthology.org/2020.findings-emnlp.261/), anri
 
 ### Usage
+Using the tokenizer (same as LegalBERT
 ```python
 from transformers import AutoTokenizer, AutoModel, BertForPreTraining
 tokenizer = AutoTokenizer.from_pretrained("nlpaueb/legal-bert-base-uncased")