nielsr
/

lilt-xlm-roberta-base

Feature Extraction PyTorch Safetensors Transformers 94 languages lilt License: mit

Model card Files Files and versions Community

Edit model card

LiLT + XLM-RoBERTa-base

This model is created by combining the Language-Independent Layout Transformer (LiLT) with XLM-RoBERTa, a multilingual RoBERTa model (trained on 100 languages).

This way, we have a LayoutLM-like model for 100 languages :)

Downloads last month: 4,478

Safetensors

Model size

284M params

Tensor type

I64

·

F32

·

Hosted inference API

Feature Extraction

This model can be loaded on the Inference API on-demand.

Spaces using nielsr/lilt-xlm-roberta-base 4