File size: 569 Bytes
162282c
 
 
 
 
 
 
eaa4ebe
162282c
 
1
2
3
4
5
6
7
8
9
10
11
# alephbertgimmel
AlephBertGimmel - Modern Hebrew pretrained BERT model with a 128K token vocabulary.

NOTE: This model was only trained with sequences of up to 128 tokens.

When using AlephBertGimmel, please reference:

Eylon Guetta, Avi Shmidman, Shaltiel Shmidman, Cheyn Shmuel Shmidman, Joshua Guedalia, Moshe Koppel, Dan Bareket, Amit Seker and Reut Tsarfaty, "Large Pre-Trained Models with Extra-Large Vocabularies: A Contrastive Analysis of Hebrew BERT Models and a New One to Outperform Them All", Nov 2022 [arXiv:2211.15199](http://arxiv.org/abs/2211.15199)