Ruri v3 delivers high‑performance Japanese text embeddings up to 8192 tokens, a 100k‑token vocabulary, FlashAttention support, and multiple model sizes (30 m–310 m) for efficient inference and fine‑tuning via sentence‑transformers.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
14,000
Hugging Face likes
5
Listed
Apr 22, 2025
Downloads (30-day window) over time
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | 6,000 |
| Jan 2026 | 3,000 |
| Feb 2026 | 3,000 |
| Mar 2026 | 12,000 |
| Apr 2026 | 16,000 |
| May 2026 | 11,000 |
| Jun 2026 | 53,000 |
| Jul 2026 | 52,000 |
| Aug 2026 | 40,000 |
| Sep 2026 | 34,000 |
| Oct 2026 | 21,000 |
| Nov 2026 | 14,000 |
Downloads over the 30 days before the last snapshot of each month.
Popular in the same category
- ruri-v3-310mcl-nagoya634kRuri v3 is a state‑of‑the‑art Japanese text‑embedding model built on ModernBERT‑Ja, supporting up to 8,192‑token inputs, a 100K‑token vocabulary, FlashAttention‑accelerated inference, and multiple size variants for fast sentence‑transformer usage.
- plamo-embedding-1bpfnet486kPLaMo‑Embedding‑1B is a Japanese text‑embedding model from Preferred Networks that converts Japanese text into vectors for information retrieval, classification, and clustering, shows strong performance on the JMTEB benchmark, and is freely available under an Apache v2.0 license.
- ruri-v3-30mcl-nagoya126kRuri v3 is a state‑of‑the‑art Japanese text embedding model built on ModernBERT‑Ja, supporting up to 8,192 tokens, a 100 k‑token vocabulary, FlashAttention acceleration, and multiple sizes from 37 M to 315 M parameters.
- ruri-v3-130mcl-nagoya93kRuri v3 is a state‑of‑the‑art Japanese text‑embedding model built on ModernBERT‑Ja, supporting up to 8192‑token sequences, a 100K‑token vocabulary, FlashAttention, and released in sizes from 30 M to 310 M parameters for use with sentence‑transformers.
- GLuCoSE-base-japkshatech31kGLuCoSE is a Japanese sentence‑embedding model built on LUKE that outputs 768‑dim mean‑pooled vectors (up to 512 tokens) trained on web and NLI/search data, achieving 0.864 Spearman and 0.818 Pearson on similarity benchmarks.
- ruri-largecl-nagoya8kA collection of release‑ready Ruri v3 Japanese text embedding models (30m–310m), complete with SentenceTransformer usage tips, query/passage prefixes, and JMTEB benchmark results showing how they compare to other Japanese and multilingual embeddings.
Resources in similar research fields
- japanese-splade-v2hotchpotch4kHigh‑performance Japanese SPLADE v2 enables sparse‑vector conversion and inference through a WebUI demo, trains with YAST, offers YASEM embedding, and reports JMTEB benchmark results.Shared: Representation Learning・Semantic Text Processing
wikipedia-passages-jawiki-embeddings-utilshotchpotch12wikipedia 日本語の文を、各種日本語の embeddings や faiss index へと変換するスクリプト等。GitHubShared: Representation Learning・Semantic Text Processing
chiVeWorksApplications179Japanese word embedding with Sudachi and NWJCGitHubShared: Representation Learning・Semantic Text Processing
ja.text8Hironsan113Japanese text8 corpus for word embedding.GitHubShared: Representation Learning・Semantic Text Processing- GLuCoSE-base-ja-v2pkshatech6kGLuCoSE v2 is a CPU‑friendly Japanese text‑embedding model, fine‑tuned by distillation and multi‑stage contrastive learning, that delivers superior semantic‑similarity and retrieval performance—outperforming comparable‑size models on MIRACL and related benchmarks.Shared: Representation Learning・Semantic Text Processing
- ruri-basecl-nagoya5kJapanese general text embedding models (Ruri‑v3, 30‑310 M parameters, 8192‑token max, high JMTEB scores) are offered with Sentence‑Transformers usage examples and benchmark comparisons to other Japanese embeddings.Shared: Representation Learning・Semantic Text Processing