bge-reranker-v2-m3-ONNX

Dakera's default reranker · a verified mirror by Dakera, the self-hosted memory engine for AI agents

An unmodified, checksum-verified copy of the files Dakera uses from BAAI/bge-reranker-v2-m3. The model is by BAAI; all credit goes to its authors.

In Dakera

A cross-encoder that re-scores the best recall candidates for every query, in about 100 languages. On by default (DAKERA_RERANKER_MODEL=bge-reranker-v2-m3).

Dakera fetches this reranker from this repository first and from the original repositories if it is unreachable, so installs never depend on a single source. Both are checked against the same SHA-256, and the Dakera Docker image ships the default models ready to run, with no download at startup.

Files

Copied byte for byte from:

File	Source	Size
onnx/model_int8.onnx	onnx-community/bge-reranker-v2-m3-ONNX	570.7 MB
tokenizer.json	onnx-community/bge-reranker-v2-m3-ONNX	17.1 MB

SHA-256 checksums

912fc1215c2dbff6499700534bd8d31253af01573861abbfc43afd1fab6cce5d  onnx/model_int8.onnx
8bf8afbfd11306bd872018c53bfdf2e160a56f8edbcf49933324404791c148d3  tokenizer.json

Licence and credit

Apache-2.0, the same as the original model (see LICENSE). For what the model does, how it was trained and how to cite it, see the original model card.

About Dakera

Dakera is a self-hosted memory engine for AI agents. It gives agents long-term memory that survives sessions: hybrid vector and full-text retrieval, reranking, entity extraction and importance decay, in a single Rust binary that runs on your own servers, with an MCP server for Claude, Cursor and other agents.

docker run -p 3000:3000 -e DAKERA_ROOT_API_KEY=dk-mykey ghcr.io/dakera-ai/dakera:latest

🌐 Website	dakera.ai
📚 Documentation	dakera.ai/docs
💻 GitHub	github.com/Dakera-AI
🚀 Self-hosting (Docker, Kubernetes, Helm)	dakera-deploy
🔌 MCP server	dakera-mcp
🧰 SDKs	Python · TypeScript · Go · Rust
💼 LinkedIn	Dakera AI

Questions or feedback: amine@dakera.ai.