Update README.md
Browse files
README.md
CHANGED
|
@@ -6,4 +6,4 @@ language:
|
|
| 6 |
<img src="https://huggingface.co/dlicari/lsg16k-Italian-Legal-BERT/resolve/main/ITALIAN_LEGAL_BERT-LSG.jpg" width="600"/>
|
| 7 |
|
| 8 |
# LSG16K-Italian-LEGAL-BERT
|
| 9 |
-
[Local-Sparse-Global](https://arxiv.org/abs/2210.15497) version of [ITALIAN-LEGAL-BERT-SC](https://huggingface.co/dlicari/Italian-Legal-BERT) by replacing the full attention in the encoder part using the LSG converter script (https://github.com/ccdv-ai/convert\_checkpoint\_to\_lsg). We used the LSG attention with 16,384 maximum sequence length, 7 global tokens, 128 local block size, 128 sparse block size, 2 sparsity factors, 'norm' sparse selection pattern (select the highest norm tokens).
|
|
|
|
| 6 |
<img src="https://huggingface.co/dlicari/lsg16k-Italian-Legal-BERT/resolve/main/ITALIAN_LEGAL_BERT-LSG.jpg" width="600"/>
|
| 7 |
|
| 8 |
# LSG16K-Italian-LEGAL-BERT
|
| 9 |
+
[Local-Sparse-Global](https://arxiv.org/abs/2210.15497) version of [ITALIAN-LEGAL-BERT-SC](https://huggingface.co/dlicari/Italian-Legal-BERT-SC) by replacing the full attention in the encoder part using the LSG converter script (https://github.com/ccdv-ai/convert\_checkpoint\_to\_lsg). We used the LSG attention with 16,384 maximum sequence length, 7 global tokens, 128 local block size, 128 sparse block size, 2 sparsity factors, 'norm' sparse selection pattern (select the highest norm tokens).
|