Modelpublic

arbazsiddiqui/opensearch-neural-sparse-multilingual-v1-GGUF

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face

0likes30downloads

Model Card

opensearch-neural-sparse-encoding-multilingual-v1 · GGUF

GGUF conversion of opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1 (168M-parameter inference-free multilingual sparse retrieval encoder, 105,879-token vocabulary), packaged for sqlite-sparse: semantic search in a single SQLite file with no model at query time. Served as the multilingual tier.

llama.cpp's converter drops the masked-LM head that sparse encoders need, so this repo ships it as a sidecar: the .sprs file carries the MLM transform, the query-weight lookup table (the "inference-free" query side), and the WordPiece vocabulary.

Files

file	what
`multilingual_f16.gguf`	encoder body, f16 (llama.cpp-loadable, per-token hidden states)
`multilingual_q8.gguf`	encoder body, Q8_0
`multilingual.sprs`	MLM head + query weight table + vocab (format v1)

Fidelity

Differentially validated against the original SentenceTransformers implementation:

—encoder hidden states, worst token: cosine 0.999996 (f16), 0.999702 (Q8_0)
—end-to-end term weights through the sidecar head: max delta 1.3e-03

Validation probes included German and Spanish sentences with exact token-count agreement between llama.cpp and HF tokenization.

Provenance

Weights are unmodified from the Apache-2.0 original by the OpenSearch project; this repo only changes container format. All retrieval-quality credit belongs to the original model.