snowflake-arctic-embed-22m

PyTorch

4 versions

A suite of text embedding models by Snowflake, optimized for performance.

Run this model

  1. Install our magic package manager:

    curl -ssL https://magic.modular.com/ | bash

    Then run the source command that's printed in your terminal.

  2. Install Max Pipelines in order to run this model.

    magic global install max-pipelines
  3. Start a local endpoint for snowflake-arctic-embed/22m:

    max-serve serve --huggingface-repo-id Snowflake/snowflake-arctic-embed-xs

    The endpoint is ready when you see the URI printed in your terminal:

    Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
  4. Now open another terminal to send a request using curl:

    curl -N http://0.0.0.0:8000/v1/chat/completions -H "Content-Type: application/json" -d '{
        "model": "snowflake-arctic-embed/22m",
        "stream": true,
        "messages": [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Who won the World Series in 2020?"}
        ]
    }' | grep -o '"content":"[^"]*"' | sed 's/"content":"//g' | sed 's/"//g' | tr -d '
    ' | sed 's/\n/
    /g'
  5. 🎉 Hooray! You’re running Generative AI. Our goal is to make this as easy as possible.

About

snowflake-arctic-embed is a family of advanced text embedding models designed to deliver high-quality retrieval performance. These models are optimized through a multi-stage training pipeline that builds upon open-source text representation models, such as bert-base-uncased.

This suite of models is tailored for robust and efficient text retrieval tasks, ensuring exceptional performance in various applications. Offered in five parameter sizes, these models provide flexibility based on resource requirements and use cases:

  • snowflake-arctic-embed-335m (default)
  • snowflake-arctic-embed-137m
  • snowflake-arctic-embed-110m
  • snowflake-arctic-embed-33m
  • snowflake-arctic-embed-22m

The models are accessible for integration and experimentation, enabling users to harness state-of-the-art text embedding capabilities.

Reference

Blog Post

HuggingFace

DETAILS

MODEL CLASS
PyTorch

MODULAR GITHUB

Modular

CREATED BY

Snowflake

MODEL

Snowflake/snowflake-arctic-embed-xs

TAGS

arctic
arxiv:2405.05374
arxiv:2407.18887
autotrain_compatible
bert
endpoints_compatible
feature-extraction
model-index
mteb
onnx
region:us
safetensors
sentence-similarity
sentence-transformers
snowflake-arctic-embed
text-embeddings-inference
transformers.js

@ Copyright - Modular Inc - 2024