Back to all models
Model: codegram/calbert-base-uncased

Monthly model downloads

codegram/calbert-base-uncased codegram/calbert-base-uncased
- downloads
last 30 days



Contributed by

Codegram company
1 team member · 2 models

How to use this model directly from the 🤗/transformers library:

Copy model
tokenizer = AutoTokenizer.from_pretrained("codegram/calbert-base-uncased") model = AutoModel.from_pretrained("codegram/calbert-base-uncased")

CALBERT: a Catalan Language Model


CALBERT is an open-source language model for Catalan based on the ALBERT architecture.

It is now available on Hugging Face in its base-uncased version, and was pretrained on the OSCAR dataset.

For further information or requests, please go to the GitHub repository

Pre-trained models

Model Arch. Training data
codegram / calbert-base-uncased Base (uncased) OSCAR (4.3 GB of text)


CALBERT was trained and evaluated by Txus Bach, as part of Codegram's applied research.