Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
language: it
|
| 3 |
-
license:
|
| 4 |
widget:
|
| 5 |
-
- text:
|
| 6 |
---
|
| 7 |
<img src="https://huggingface.co/dlicari/Italian-Legal-BERT-SC/resolve/main/ITALIAN_LEGAL_BERT-SC.jpg" width="600"/>
|
| 8 |
|
|
@@ -13,6 +13,4 @@ It is the [ITALIAN-LEGAL-BERT](https://huggingface.co/dlicari/Italian-Legal-BERT
|
|
| 13 |
It was trained from scratch using a larger training dataset, 6.6GB of civil and criminal cases.
|
| 14 |
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,
|
| 15 |
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)
|
| 16 |
-
and vocabulary size of 32000
|
| 17 |
-
|
| 18 |
-
|
|
|
|
| 1 |
---
|
| 2 |
language: it
|
| 3 |
+
license: afl-3.0
|
| 4 |
widget:
|
| 5 |
+
- text: Il <mask> ha chiesto revocarsi l'obbligo di pagamento
|
| 6 |
---
|
| 7 |
<img src="https://huggingface.co/dlicari/Italian-Legal-BERT-SC/resolve/main/ITALIAN_LEGAL_BERT-SC.jpg" width="600"/>
|
| 8 |
|
|
|
|
| 13 |
It was trained from scratch using a larger training dataset, 6.6GB of civil and criminal cases.
|
| 14 |
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,
|
| 15 |
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)
|
| 16 |
+
and vocabulary size of 32000
|
|
|
|
|
|