Using BGE Reranker V2 M3 on Novita AI
Implementation guide · BGE · Beijing Academy of Artificial Intelligence (BAAI)
Serverless
Quick Start
- 1
- 2Use the Novita AI SDK or REST API to call
bge-reranker-v2-m3. - 3
Code Examples
Code examples for this provider have not been sourced yet.
About Novita AI
Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.
Pricing on Novita AI
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.01 |
Capabilities
No model capability flags are currently sourced.
About BGE Reranker V2 M3
BGE Reranker V2 M3 is BAAI's lightweight multilingual cross-encoder reranking model from the FlagEmbedding project, based on the BGE-M3 backbone. Accepts query-passage pairs and outputs direct relevance scores. Supports multi-lingual processing with 568 million parameters. Part of the BGE reranker v2 series released March 2024 alongside LLM-based rerankers.
Model Specs
Released2024-03-18
Parameters568M
Context8K
Architectureencoder_only