metadata
language: pt
license: mit
tags:
- msmarco
- miniLM
- pytorch
- tensorflow
- pt
- pt-br
datasets:
- msmarco
widget:
- text: Texto de exemplo em português
inference: false
multilingual-MiniLM-L6-v2-multi-msmarco Reranker finetuned on Multi MS MARCO
Introduction
multilingual-MiniLM-L6-v2-multi-msmarco is a multilingual miniLM-based model finetuned on a multilingual version of MS MARCO passage dataset. This dataset, named mMARCO, is formed by passages in 8 different languages, translated from English MS MARCO passages collection. Further information about the dataset or the translation method can be found on our Cross-Lingual repository.
Usage
from transformers import AutoTokenizer, AutoModel
model_name = 'unicamp-dl/multilingual-MiniLM-L6-v2-multi-msmarco'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name)