Downloads · 30 days
24
29% of all-time downloads
arbazsiddiqui/opensearch-neural-sparse-multilingual-v1-GGUF
opensearch-neural-sparse-multilingual-v1-GGUF is a feature extraction model from arbazsiddiqui. Use it when you need embeddings to search or compare text. The card lists the license as apache-2.0.
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:
Downloads · 30 days
24
29% of all-time downloads
All-time downloads
84
Public
Repo size
847 MB
Likes
0
Public
Click a slice to open those files.
.gguf518 MB · 61%
From the Hugging Face model README
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.
| 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) |
Differentially validated against the original SentenceTransformers implementation:
Validation probes included German and Spanish sentences with exact token-count agreement between llama.cpp and HF tokenization.
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.