Models / intfloat
Embeddings

Multilingual e5 large instruct

Instruction-tuned multilingual embedding model trained on 1B+ pairs across 93 languages, excelling in retrieval tasks.

About model

Multilingual E5 large instruct generates text embeddings for multilingual text retrieval tasks, excelling at capturing semantic meaning across languages. It is suitable for developers and researchers working with multilingual text data.

To use this embeddings model, please follow the instructions from our Docs.

  • API usage

    • cURL
    • Python
    • Typescript

    Endpoint:

    intfloat/multilingual-e5-large-instruct

    curl -X POST https://api.together.xyz/v1/embeddings \
      -H "Authorization: Bearer $TOGETHER_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "input": "Our solar system orbits the Milky Way galaxy at about 515,000 mph.",
        "model": "intfloat/multilingual-e5-large-instruct"
      }'
    
    from together import Together
    
    client = Together()
    
    response = client.embeddings.create(
      model = "intfloat/multilingual-e5-large-instruct",
      input = "Our solar system orbits the Milky Way galaxy at about 515,000 mph"
    )
    
    
    import Together from "together-ai";
    
    const together = new Together();
    
    const response = await client.embeddings.create({
      model: 'intfloat/multilingual-e5-large-instruct',
      input: 'Our solar system orbits the Milky Way galaxy at about 515,000 mph',
    });
    
    
Related models
  • Model provider
    intfloat
  • Type
    Embeddings
  • Main use cases
    Embeddings
  • Deployment
    Serverless
    On-Demand Dedicated
    Monthly Reserved
  • Parameters
    559.9M
  • Context length
    514
  • Input price

    $0.02 / 1M tokens

  • Output price

    $0.02 / 1M tokens

  • Input modalities
    Text
  • Output modalities
    Structured Data
  • Released
    February 8, 2024
  • External link
  • Category
    Embeddings