BERT: differenze tra le versioni
(Creata pagina con " === Links === [https://arxiv.org/pdf/1810.04805.pdf BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (24/05/2019)] [https://arxiv.org/pdf/1905.05583.pdf How to Fine Tune Bert for Sequence Classification?] https://www.kaggle.com/discussions/questions-and-answers/86510 [https://arxiv.org/abs/1908.10084 Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (SBERT)]: modello successivo a BERT con migliori risultati sui benchmar...") |
Nessun oggetto della modifica |
||
| Riga 11: | Riga 11: | ||
https://discuss.huggingface.co/t/significance-of-the-cls-token/3180 | https://discuss.huggingface.co/t/significance-of-the-cls-token/3180 | ||
[[Category:Modello]] | |||
Versione delle 20:34, 23 mar 2024
Links
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (24/05/2019)
How to Fine Tune Bert for Sequence Classification?
https://www.kaggle.com/discussions/questions-and-answers/86510
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (SBERT): modello successivo a BERT con migliori risultati sui benchmark di Semantic Textual Similarity (STS)
https://discuss.huggingface.co/t/significance-of-the-cls-token/3180