--- license: mit language: - it widget: - text: "Milano è una italiana" example_title: "Example 1" - text: "Leopardi è stato uno dei più grandi del classicismo italiano" example_title: "Example 2" - text: "L'Italia è uno dell'Unione Europea" example_title: "Example 3" --- --------------------------------------------------------------------------------------------------  
  
    Model: RoBERTa
    Lang: IT
  
  --------------------------------------------------------------------------------------------------

Model description

This is a RoBERTa [1] model for the Italian language, obtained using XLM-RoBERTa [2] ([xlm-roberta-base](https://huggingface.co/xlm-roberta-base)) as a starting point and focusing it on the italian language by modifying the embedding layer (as in [3], computing document-level frequencies over the Wikipedia dataset) The resulting model has 125M parameters, a vocabulary of 50.670 tokens, and a size of ~500 MB.

Quick usage

```python from transformers import RobertaTokenizerFast, RobertaModel tokenizer = RobertaTokenizerFast.from_pretrained("osiria/roberta-base-italian") model = RobertaModel.from_pretrained("osiria/roberta-base-italian") ```

References

[1] https://arxiv.org/abs/1907.11692 [2] https://arxiv.org/abs/1911.02116 [3] https://arxiv.org/abs/2010.05609

License

The model is released under MIT license