Skip to main content
Version: 1.28

Multilingual E5 Large

Multilingual E5 Large Instruct is an embedding model that was initialized from xlm-roberta-large and continually trained on a mixture of multilingual datasets. It supports 100 languages from xlm-roberta.

Model ID​

multilingual-e5-large

Source​

Hugging face

Modality​

  • Input: text
  • Output: embedding vector

Context limit​

  • Embedding size: 1024; the model doesn't support reduced dimensions
  • Maximum input size: 512 tokens

Endpoints​