Fast, lightweight Japanese Reranker v2 models (tiny, xsmall, small, base) with benchmark scores and GPU speeds, usable via sentence_transformers CrossEncoder and transformers ≥ v4.48 (optionally accelerated with flash‑attn) and also available in ONNX/quantized forms for CPU/ARM.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
28,000
Hugging Face likes
7
Listed
May 13, 2025
Downloads (30-day window) over time
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | 13,000 |
| Jan 2026 | 5,000 |
| Feb 2026 | 7,000 |
| Mar 2026 | 18,000 |
| Apr 2026 | 9,000 |
| May 2026 | 17,000 |
| Jun 2026 | 44,000 |
| Jul 2026 | 72,000 |
| Aug 2026 | 92,000 |
| Sep 2026 | 150,000 |
| Oct 2026 | 25,000 |
| Nov 2026 | 28,000 |
Downloads over the 30 days before the last snapshot of each month.
Popular in the same category
- japanese-reranker-cross-encoder-small-v1hotchpotch156kJapanese‑trained CrossEncoder rerankers ranging from xsmall (384) to large (1024) plus a BGE‑v2‑m3‑v1 model, with example code for fine‑tuning, inference, and benchmark scores on JQaRA, JaCWIR, MIRACL, and JSQuAD.
- ruri-v3-reranker-310mcl-nagoya137kRuri‑v3 Reranker is a robust Japanese text reranker built on ModernBERT‑Ja, supporting up to 8,192‑token sequences, a 100k‑token vocabulary, FlashAttention and a SentencePiece tokenizer, and it can be used via sentence‑transformers.
- japanese-reranker-cross-encoder-xsmall-v1hotchpotch16kJapanese CrossEncoder reranker models ranging from xsmall to large (plus BGE), evaluated on JQaRA, JaCWIR, MIRACL, and JSQuAD, with ready‑to‑use integration examples for sentence_transformers and HuggingFace.
- ruri-reranker-smallcl-nagoya3kJapanese‑language reranker models built with Sentence Transformers (cross‑encoders) that can be loaded via trust_remote_code, benchmarked on JQaRA, JaCWIR, and MIRACL datasets, and available in small to large sizes from the hotchpotch organization.
- japanese-reranker-tiny-v2hotchpotch2kA compact, high‑speed Japanese reranker library (v2) offering tiny‑through‑base and cross‑encoder models with detailed latency and accuracy statistics, requiring Transformers ≥ 4.48 (optionally Flash‑Attention 2) and supporting ONNX/quantization for CPU/ARM deployments.
- japanese-reranker-small-v2hotchpotch2kJapanese‑reranker‑small‑v2 is a lightweight, fast Japanese reranker model series (v2) offering tiny to base variants that reach up to 0.89 average score with 2–15 s GPU inference, plus cross‑encoder options, and requires Hugging Face Transformers v4.48+ with optional Flash Attention 2 for acceleration.
Resources in similar research fields
daachorsedaac-tools286A fast implementation of the Aho-Corasick algorithm using the compact double-array data structure in Rust.GitHubShared: Information Retrieval・Indexing
crawdaddaac-tools40Rust library of natural language dictionaries using character-wise double-array tries.GitHubShared: Information Retrieval・Indexing
lindera-sqlitelindera24Lindera for SQLite FTS5 extentionGitHubShared: Indexing・Information Retrieval
sqlite-vaporettohotchpotch20SQLite FTS5 extension for fast Japanese full-text search with 🛥Vaporetto / Vaporetto による高速な日本語全文検索を SQLite FTS5 で実現する拡張機能GitHubShared: Indexing・Information Retrieval
minimal-search-engineGINK0319Smallest search engine/PageRank/tf-idfGitHubShared: Information Retrieval・Indexing
duckdb-vaporettohotchpotch11DuckDB extension for Japanese full-text search with 🛥Vaporetto / Vaporetto による DuckDB + 日本語全文検索拡張機能GitHubShared: Indexing・Information Retrieval