telepix
/

PIXIE-Splade-Preview

Feature Extraction

sentence-transformers

sentence-similarity

text-embeddings-inference

Model card Files Files and versions

BM-K commited on Aug 11, 2025

Commit

6258672

·

verified ·

1 Parent(s): 78815f7

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ compatible with inverted indexing (e.g., Lucene/Elasticsearch).
 Because each non-zero weight corresponds to a Korean subword/token,
 interpretability is built-in: you can inspect which tokens drive retrieval.
-## Why SPLADE for Korean Search?
 - **Inverted Index Ready**: Directly index weighted tokens in standard IR stacks (Lucene/Elasticsearch).
 - **Interpretable by Design**: Top-k contributing tokens per query/document explain *why* a hit matched.
 - **Production-Friendly**: Fast candidate generation at web scale; memory/latency tunable via sparsity thresholds.

 Because each non-zero weight corresponds to a Korean subword/token,
 interpretability is built-in: you can inspect which tokens drive retrieval.
+## Why SPLADE for Search?
 - **Inverted Index Ready**: Directly index weighted tokens in standard IR stacks (Lucene/Elasticsearch).
 - **Interpretable by Design**: Top-k contributing tokens per query/document explain *why* a hit matched.
 - **Production-Friendly**: Fast candidate generation at web scale; memory/latency tunable via sparsity thresholds.