Japanese Sentence‑BERT (v1) model for generating sentence embeddings, with an improved v2 available and sample usage via Hugging Face Transformers and a custom SentenceBertJapanese class.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
14,000
Hugging Face likes
11
Listed
—
Listed since the page was created
Downloads (30-day window) over time
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | 24,000 |
| Jan 2026 | 23,000 |
| Feb 2026 | 39,000 |
| Mar 2026 | 47,000 |
| Apr 2026 | 141,000 |
| May 2026 | 318,000 |
| Jun 2026 | 23,000 |
| Jul 2026 | 18,000 |
| Aug 2026 | 14,000 |
| Sep 2026 | 14,000 |
| Oct 2026 | 19,000 |
| Nov 2026 | 14,000 |
Downloads over the 30 days before the last snapshot of each month.
Popular in the same category
- sentence-bert-base-ja-mean-tokens-v2sonoisa53kA Japanese Sentence‑BERT v2, fine‑tuned on cl‑tohoku/bert‑base‑japanese‑whole‑word‑masking with MultipleNegativesRankingLoss, boosts accuracy by ~1.5–2 % over v1 and is released as sonoisa/sentence‑bert‑base‑ja‑mean‑tokens‑v2.
- clip-japanese-baseline-corporation34kLY Corporation’s clip‑japanese‑base is a Japanese CLIP model trained on ~1 B image‑text pairs, using an Eva02‑B transformer image encoder with a 12‑layer BERT text encoder, achieving R@1 0.30 on STAIR, 0.89 accuracy on Recruit and 0.58 accuracy on ImageNet‑1K, and supporting zero‑shot image classification and retrieval.
- transformers-ud-japanese-electra-base-ginza-510megagonlabs22kja_ginza_electra is a spaCy v3 Python package offering a Japanese ELECTRA model fine‑tuned on mC4 and UD_Japanese_BCCWJ r2.8 (based on megagonlabs/transformers‑ud‑japanese‑electra‑base‑discrimininator) with custom bunsetu‑phrase detection, distributed under the MIT license.
- sentence-luke-japanese-base-litesonoisa10kJapanese Sentence‑LUKE model trained on the same dataset as Sentence‑BERT, outperforming or matching it, built on studio‑ousia/luke‑japanese‑base‑lite and used via Hugging Face Transformers’ MLukeTokenizer and LukeModel.
- clip-japanese-base-v2line-corporation2kJapanese CLIP model clip‑japanese‑base‑v2, upgraded with ~2 B image‑text pairs and distillation, pairs an Eva02‑B image encoder with a 12‑layer BERT text encoder to reach higher ImageNet‑1k accuracy (0.708) than its predecessor.
- sup-simcse-ja-basecl-nagoya2kA Japanese BERT‑base model fine‑tuned with supervised SimCSE on JSNLI, exposed via Sentence‑Transformers or HuggingFace with CLS pooling, trained on 1 M examples at 512‑batch size, 5 × 10⁻⁵ learning rate, 5 × 10⁻⁵ temperature, 64‑token limit, and BFloat16 precision.
Resources in similar research fields
- bert-large-japanese-v2tohoku-nlp66kJapanese‑BERT‑Large trained on CC‑100 and Wikipedia, using Unidic‑lite word‑level tokenization with WordPiece subwords and whole‑word masking (24 layers, 1024‑dim hidden, 16 heads, 32k vocab), with pretraining code on cl‑tohoku/bert‑japanese.Shared: Representation Learning・Language Models
- bert-base-japanese-v3tohoku-nlp66kJapanese BERT‑base (12 layers, 768‑dim hidden, 12 heads, 32 k vocab) pretrained with whole‑word masking on CC‑100 and 2023‑Jan Wikipedia, using Unidic 2.1.2 word‑level tokenization plus WordPiece, in 2 M training steps.Shared: Representation Learning・Language Models
bert-japanesecl-tohoku551BERT models for Japanese language text.GitHubShared: Representation Learning・Language Models- 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.Shared: Representation Learning・Language Models
- 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.Shared: Representation Learning・Semantic Text Processing
- 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.Shared: Representation Learning・Semantic Text Processing