nlpai-lab
/

KURE-v2

Sentence Similarity

sentence-transformers

late-interaction

feature-extraction

text-embeddings-inference

Model card Files Files and versions

yjoonjang commited on Aug 29

Commit

4e9f85c

·

verified ·

1 Parent(s): 4704854

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -221,7 +221,7 @@ Three things the figures show:
 - Hierarchical token pooling (x2) halves the index for a 0.04 nDCG drop. Asymmetric binary quantization (1-bit document tokens, bf16 queries) shrinks it 9.4x for 1.05. Stacking the two (pooling x3 + binary), the entire 9-corpus index fits in **1.7 GB, smaller than every single-vector HNSW index (13.1-50.0 GB)**, while still outscoring the best single-vector model (79.57 vs 79.07).
 - A live query arrives as text: 4B-8B single-vector models spend 38-40 ms encoding it, capping them at ~25 QPS no matter how fast HNSW is. KURE-v2 encodes in 13.8 ms (154M params), so every configuration except MUVERA serves **43-55 QPS, roughly 2x the 8B single-vector models, at higher quality**.
-- Official fast-plaid at default settings: top quality (81.43), encode-bound throughput, and residual compression that scales cleanly to the 1.5M-doc corpora.
 ### Large corpora: tail latency

 - Hierarchical token pooling (x2) halves the index for a 0.04 nDCG drop. Asymmetric binary quantization (1-bit document tokens, bf16 queries) shrinks it 9.4x for 1.05. Stacking the two (pooling x3 + binary), the entire 9-corpus index fits in **1.7 GB, smaller than every single-vector HNSW index (13.1-50.0 GB)**, while still outscoring the best single-vector model (79.57 vs 79.07).
 - A live query arrives as text: 4B-8B single-vector models spend 38-40 ms encoding it, capping them at ~25 QPS no matter how fast HNSW is. KURE-v2 encodes in 13.8 ms (154M params), so every configuration except MUVERA serves **43-55 QPS, roughly 2x the 8B single-vector models, at higher quality**.
+- Official fast-plaid at default settings: top quality, encode-bound throughput, and residual compression that scales cleanly to the 1.5M-doc corpora.
 ### Large corpora: tail latency