BGE m3

Summary: Embedding model to map long multilingual text to a 1024 dimensional dense vector space.

Intelligence

Speed

Sovereignty

Input

Output

High

Medium

Medium

Text

Number Vector

Central parameters

Description: BGE m3 is an embedding model trained by the Beijing Academy of Artificial Intelligence to map sentences and paragraphs to a 1024-dimensional dense vector space. It supports 100 different languages with high performance and long input lengths. It can be used for tasks like clustering or semantic search.

Model identifier: BAAI/bge-m3

IONOS AI Model Hub Lifecycle and Alternatives

IONOS Launch

End of Life

Alternative

Successor

January 1, 2025

N/A

Origin

Provider

Country

License

Flavor

Release

Community

-

January 28, 2024

Technology

Input Length

Parameters

Tensor Type

Multilingual

8192

568M

float

Yes

Modalities

Text

Image

Audio

Input and output

Not supported

Not supported

Endpoints

Chat Completions

Embeddings

Image generation

Not supported

v1/embeddings

Not supported

Features

Streaming

Tool calling

Not supported

Not supported

Rate limits

Rate limits ensure fair usage and reliable access to the AI Model Hub. In addition to the contract-wide rate limits, no model-specific limits apply.

Last updated

Was this helpful?