Update README.md
Browse files
README.md
CHANGED
|
@@ -40,7 +40,7 @@ model-index:
|
|
| 40 |
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
| 41 |
stjiris/bert-large-portuguese-cased-legal-mlm-sts-v0 derives from [BERTimbau](https://huggingface.co/neuralmind/bert-large-portuguese-cased) large.
|
| 42 |
|
| 43 |
-
It was trained using the MLM technique with a learning rate 3e-5 [Legal Sentences from +-30000 documents](https://huggingface.co/datasets/stjiris/portuguese-legal-sentences-v0) 130k training steps (best performance)
|
| 44 |
|
| 45 |
It is adapted to the Portuguese legal domain and trained for STS on portuguese datasets. [assin](https://huggingface.co/datasets/assin), [assin2](https://huggingface.co/datasets/assin2) and [stsb_multi_mt](https://huggingface.co/datasets/stsb_multi_mt) portuguese subdataset
|
| 46 |
|
|
|
|
| 40 |
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
| 41 |
stjiris/bert-large-portuguese-cased-legal-mlm-sts-v0 derives from [BERTimbau](https://huggingface.co/neuralmind/bert-large-portuguese-cased) large.
|
| 42 |
|
| 43 |
+
It was trained using the MLM technique with a learning rate 3e-5 [Legal Sentences from +-30000 documents](https://huggingface.co/datasets/stjiris/portuguese-legal-sentences-v0) 130k training steps (best performance for our semantic search system implementation)
|
| 44 |
|
| 45 |
It is adapted to the Portuguese legal domain and trained for STS on portuguese datasets. [assin](https://huggingface.co/datasets/assin), [assin2](https://huggingface.co/datasets/assin2) and [stsb_multi_mt](https://huggingface.co/datasets/stsb_multi_mt) portuguese subdataset
|
| 46 |
|