Downloads · 30 days
52
51% of all-time downloads
arbazsiddiqui/opensearch-neural-sparse-doc-v3-distill-GGUF
opensearch-neural-sparse-doc-v3-distill-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-doc-v3-distill (67M-parameter inference-free sparse retrieval encoder, current v3 generation), packaged for sqlite-sparse:
Downloads · 30 days
52
51% of all-time downloads
All-time downloads
102
Public
Repo size
303 MB
Likes
0
Public
Click a slice to open those files.
.gguf207 MB · 68%
From the Hugging Face model README
GGUF conversion of opensearch-project/opensearch-neural-sparse-encoding-doc-v3-distill
(67M-parameter inference-free sparse retrieval encoder, current v3 generation), packaged for sqlite-sparse:
semantic search in a single SQLite file with no model at query time. Served as the
base 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.
This v3 model uses double-log saturation (log1p(log1p(relu(x)))); the sidecar's
header carries an activation flag so runtimes apply the right formula.
| file | what |
|---|---|
base_f16.gguf | encoder body, f16 (llama.cpp-loadable, per-token hidden states) |
base_q8.gguf | encoder body, Q8_0 |
base.sprs | MLM head + query weight table + vocab (format v1) |
Differentially validated against the original SentenceTransformers implementation:
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.