Add Dutch pre-trained BERT model

This commit is contained in:
Wietse de Vries
2019-12-19 13:28:53 +01:00
committed by Julien Chaumond
parent 6b4c3ee234
commit f5a236c3ca
5 changed files with 10 additions and 0 deletions

View File

@@ -88,6 +88,10 @@ For a list that includes community-uploaded models, refer to `https://huggingfac
| | ``bert-base-finnish-uncased-v1`` | | 12-layer, 768-hidden, 12-heads, 110M parameters. |
| | | | Trained on uncased Finnish text. |
| | | (see `details on turkunlp.org <http://turkunlp.org/FinBERT/>`__). |
| +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
| | ``bert-base-dutch-cased`` | | 12-layer, 768-hidden, 12-heads, 110M parameters. |
| | | | Trained on cased Dutch text. |
| | | (see `details on wietsedv repository <https://github.com/wietsedv/bertje/>`__). |
+-------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
| GPT | ``openai-gpt`` | | 12-layer, 768-hidden, 12-heads, 110M parameters. |
| | | | OpenAI GPT English model |