osiria's picture
Update README.md
a1babbe
|
raw
history blame
2.16 kB
---
license: mit
language:
- it
widget:
- text: "Milano è una <mask> italiana"
example_title: "Example 1"
- text: "Leopardi è stato uno dei più grandi <mask> del classicismo italiano"
example_title: "Example 2"
- text: "L'Italia è uno <mask> dell'Unione Europea"
example_title: "Example 3"
---
--------------------------------------------------------------------------------------------------
<body>
<span class="vertical-text" style="background-color:lightgreen;border-radius: 3px;padding: 3px;"></span>
<br>
<span class="vertical-text" style="background-color:orange;border-radius: 3px;padding: 3px;">  </span>
<br>
<span class="vertical-text" style="background-color:lightblue;border-radius: 3px;padding: 3px;">    Model: RoBERTa</span>
<br>
<span class="vertical-text" style="background-color:tomato;border-radius: 3px;padding: 3px;">    Lang: IT</span>
<br>
<span class="vertical-text" style="background-color:lightgrey;border-radius: 3px;padding: 3px;">  </span>
<br>
<span class="vertical-text" style="background-color:#CF9FFF;border-radius: 3px;padding: 3px;"></span>
</body>
--------------------------------------------------------------------------------------------------
<h3>Model description</h3>
This is a <b>RoBERTa</b> <b>[1]</b> model for the <b>italian</b> language, obtained using <b>XLM-RoBERTa</b> <b>[2]</b> ([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 <b>[3]</b>, computing document-level frequencies over the <b>Wikipedia</b> dataset)
The resulting model has 125M parameters, a vocabulary of 50.670 tokens, and a size of ~500 MB.
<h3>Quick usage</h3>
```python
from transformers import RobertaTokenizerFast, RobertaModel
tokenizer = RobertaTokenizerFast.from_pretrained("osiria/roberta-base-italian")
model = RobertaModel.from_pretrained("osiria/roberta-base-italian")
```
<h3>References</h3>
[1] https://arxiv.org/abs/1907.11692
[2] https://arxiv.org/abs/1911.02116
[3] https://arxiv.org/abs/2010.05609
<h3>License</h3>
The model is released under <b>MIT</b> license