Update README.md

README.md

@@ -7,7 +7,16 @@ tags:
 - transformers
 ---
 
-# {MODEL_NAME}
+<img  src="https://huggingface.co/dlicari/distil-ita-legal-bert/resolve/main/ITALIAN_LEGAL_BERT-DI.jpg" width="600"/> 
+
+# Distil-ITA-Legal-BERT
+We used the process of knowledge distillation to create a fast, lightweight student model with only 4-levels of Transformers,
+capable of producing sentence embeddings similar to those produced by the more complex
+[ITALIAN-LEGAL-BERT](dlicari/Italian-Legal-BERT) teacher model. 
+
+It optimized on the ITALIAN-LEGAL-BERT train set (3.7 GB) using Sentence-BERT library by minimizing the mean square error (MSE) between its embeddings
+and those produced by the teacher model.
+
 
 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
@@ -27,7 +36,7 @@ Then you can use the model like this:
 from sentence_transformers import SentenceTransformer
 sentences = ["This is an example sentence", "Each sentence is converted"]
 
-model = SentenceTransformer('{MODEL_NAME}')
+model = SentenceTransformer('dlicari/distil-ita-legal-bert')
 embeddings = model.encode(sentences)
 print(embeddings)
 ```
@@ -53,8 +62,8 @@ def mean_pooling(model_output, attention_mask):
 sentences = ['This is an example sentence', 'Each sentence is converted']
 
 # Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
-model = AutoModel.from_pretrained('{MODEL_NAME}')
+tokenizer = AutoTokenizer.from_pretrained('dlicari/distil-ita-legal-bert')
+model = AutoModel.from_pretrained('dlicari/distil-ita-legal-bert')
 
 # Tokenize sentences
 encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')