gte-reranker-modernbert-base GGUF (Q8_0)

A GGUF conversion of Alibaba-NLP/gte-reranker-modernbert-base, used as the optional reranker in The People's Solutions meeting-notes app. The app downloads this file by commit-pinned URL and checks the hash below before using it.

Provenance

• Source weights: Alibaba-NLP/gte-reranker-modernbert-base at revision f7481e6055501a30fb19d090657df9ec1f79ab2c.
• Converter: llama.cpp convert_hf_to_gguf.py at commit a0e6dc7384edb8f5d927155e1d26c10b4a310e6d, output type q8_0.
• The conversion is reproducible: running the converter at that commit on that revision gives the hash above.

git clone https://github.com/ggml-org/llama.cpp && git -C llama.cpp checkout a0e6dc7384edb8f5d927155e1d26c10b4a310e6d
hf download Alibaba-NLP/gte-reranker-modernbert-base --revision f7481e6055501a30fb19d090657df9ec1f79ab2c --local-dir src
python llama.cpp/convert_hf_to_gguf.py src --outtype q8_0 --outfile gte-reranker-modernbert-base-Q8_0.gguf
shasum -a 256 gte-reranker-modernbert-base-Q8_0.gguf

License

Apache License 2.0, the same license as the source model. See LICENSE and NOTICE. The weights were changed only by format conversion and 8-bit quantization.