Commit
•
2f08d5e
1
Parent(s):
63af604
Update README.md
Browse files
README.md
CHANGED
@@ -25,7 +25,7 @@ To train ElhBERTeu, we collected different corpora sources from several domains:
|
|
25 |
|
26 |
ElhBERTeu is a base, cased monolingual BERT model for Basque, with a vocab size of 50K, which has 124M parameters in total.
|
27 |
|
28 |
-
ElhBERTeu was trained following the design decisions for [BERTeus](https://huggingface.co/ixa-ehu/berteus-base-cased). The tokenizer and the hyper-parameter settings remained the same, with the only difference being that the full pre-training of the model (1M steps) was performed with a
|
29 |
|
30 |
The model has been evaluated on the recently created [BasqueGLUE](https://github.com/Elhuyar/BasqueGLUE) NLU benchmark:
|
31 |
|
|
|
25 |
|
26 |
ElhBERTeu is a base, cased monolingual BERT model for Basque, with a vocab size of 50K, which has 124M parameters in total.
|
27 |
|
28 |
+
ElhBERTeu was trained following the design decisions for [BERTeus](https://huggingface.co/ixa-ehu/berteus-base-cased). The tokenizer and the hyper-parameter settings remained the same, with the only difference being that the full pre-training of the model (1M steps) was performed with a batch_size of 256 and a sequence_length of 512 on a v3-8 TPU.
|
29 |
|
30 |
The model has been evaluated on the recently created [BasqueGLUE](https://github.com/Elhuyar/BasqueGLUE) NLU benchmark:
|
31 |
|