roberta-base-french / README.md
ClassCat's picture
Create README.md
35f64bc
|
raw
history blame
757 Bytes
metadata
language: fr
license: cc-by-sa-4.0
datasets:
  - wikipedia
  - cc100
widget:
  - text: Je m'appele <mask>.
  - text: Je vais à <mask>.

RoBERTa French 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

Usage

from transformers import pipeline

unmasker = pipeline('fill-mask', model='ClassCat/roberta-base-french')
unmasker("Je vais à la <mask>.")