Update README.md

README.md

@@ -13,8 +13,19 @@ It achieves better results than the ‘general-purpose’ Italian BERT in differ
 
 <h2>Training procedure</h2> 
 We initialized ITALIAN-LEGAL-BERT with ITALIAN XXL BERT
-and pretrained for an additional 4 epochs on 3.7 GB of text from the National Jurisprudential
+and pretrained for an additional 4 epochs on 3.7 GB of preprocessed text from the National Jurisprudential
 Archive using the Huggingface PyTorch-Transformers library. We used BERT architecture
 with a language modeling head on top, AdamW Optimizer, initial learning rate 5e-5 (with
 linear learning rate decay, ends at 2.525e-9), sequence length 512, batch size 10 (imposed
-by GPU capacity), 8.4 million training steps, device 1*GPU V100 16GB
+by GPU capacity), 8.4 million training steps, device 1*GPU V100 16GB
+
+## Usage
+
+ITALIAN-LEGAL-BERT model can be loaded like:
+
+```python
+from transformers import AutoModel, AutoTokenizer
+model_name = "dlicari/Italian-Legal-BERT"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModel.from_pretrained(model_name)
+```