Ruri‑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.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
137,000
Hugging Face likes
18
Listed
Dec 15, 2025
Downloads (30-day window) over time
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | 7,000 |
| Jan 2026 | 9,000 |
| Feb 2026 | 11,000 |
| Mar 2026 | 9,000 |
| Apr 2026 | 64,000 |
| May 2026 | 39,000 |
| Jun 2026 | 266,000 |
| Jul 2026 | 286,000 |
| Aug 2026 | 325,000 |
| Sep 2026 | 300,000 |
| Oct 2026 | 322,000 |
| Nov 2026 | 137,000 |
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.
- japanese-reranker-xsmall-v2hotchpotch28kFast, 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.
- 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
kanjigridminosvasilias45A web-app displaying the 2200 kanji characters taught in James Heisig's "Remembering the Kanji", 6th edition.GitHubShared: Information Retrieval- japanese-reranker-base-v2hotchpotch2kA Japanese Reranker v2 suite that publishes CrossEncoder and base models from tiny to large, each with benchmark scores and GPU inference times, and requires HuggingFace Transformers ≥ 4.48 (optionally flash‑attn for faster inference).Shared: Information Retrieval
symptom-expression-searchpo3rin2I tried a semantic structure search that absorbs patient expression variations using Elasticsearch, GiNZA, and a patient expression dictionary.GitHubShared: Information Retrieval
aozorasearchmyokoym21The full-text search system for Aozora Bunko by Groonga. 青空文庫全文検索ライブラリ兼Webアプリ。GitHubShared: Information Retrieval
daachorsedaac-tools286A fast implementation of the Aho-Corasick algorithm using the compact double-array data structure in Rust.GitHubShared: Information Retrieval
elasticsearch-sudachiworksapplications220The Japanese analysis plugin for elasticsearchGitHubShared: Information Retrieval