Update README.md

README.md

@@ -13,4 +13,32 @@ It is the [ITALIAN-LEGAL-BERT](https://huggingface.co/dlicari/Italian-Legal-BERT
 It was trained from scratch using a larger training dataset, 6.6GB of civil and criminal cases. 
 We used [CamemBERT](https://huggingface.co/docs/transformers/main/en/model_doc/camembert) architecture with a language modeling head on top, AdamW Optimizer, initial learning rate 2e-5 (with linear learning rate decay), sequence length 512, batch size 18, 1 million training steps,
 device 8*NVIDIA A100 40GB using distributed data parallel (each step performs 8 batches). It uses SentencePiece tokenization trained from scratch on a subset of training set (5 milions sentences) 
-and vocabulary size of 32000
+and vocabulary size of 32000
+
+
+<h2> Usage </h2> 
+
+ITALIAN-LEGAL-BERT model can be loaded like:
+
+```python
+from transformers import AutoModel, AutoTokenizer
+model_name = "dlicari/Italian-Legal-BERT-SC"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModel.from_pretrained(model_name)
+```
+
+You can use the Transformers library fill-mask pipeline to do inference with ITALIAN-LEGAL-BERT. 
+```python
+# %pip install sentencepiece 
+# %pip install transformers
+
+from transformers import pipeline
+model_name = "dlicari/Italian-Legal-BERT-SC"
+fill_mask = pipeline("fill-mask", model_name)
+fill_mask("Il  <mask> ha chiesto revocarsi l'obbligo di pagamento")
+# [{'score': 0.6529251933097839,'token_str': 'ricorrente',
+#  {'score': 0.0380014143884182, 'token_str': 'convenuto',
+#  {'score': 0.0360226035118103,  'token_str': 'richiedente',
+#  {'score': 0.023908283561468124,'token_str': 'Condominio',  
+#  {'score': 0.020863816142082214, 'token_str': 'lavoratore'}]
+```