ClassCat's picture
Update README.md
ee1ffad
|
raw
history blame
887 Bytes
metadata
language: es
license: cc-by-sa-4.0
datasets:
  - wikipedia
  - cc100
widget:
  - text: Yo vivo en <mask>.
  - text: Es clima es <mask>.
  - text: Me llamo <mask>.
  - text: Las negociaciones están <mask>.
  - text: Las <mask> de la continuidad de Raúl en el Castilla.

RoBERTa Spanish base model (Uncased)

Prerequisites

transformers==4.19.2

Model architecture

This model uses RoBERTa base setttings except vocabulary size.

Tokenizer

Using BPE tokenizer with vocabulary size 50,000.

Training Data

  • wiki40b/es (Spanish Wikipedia)
  • Subset of CC-100/es : Monolingual Datasets from Web Crawl Data

Usage

from transformers import pipeline

unmasker = pipeline('fill-mask', model='ClassCat/roberta-base-spanish')
unmasker("Yo soy <mask>.")