Model reference · open weights

ruri

ruri is an open-weight embedding model from cl-nagoya, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Embeddings cl-nagoya 1 variants 427k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What ruri is

Ruri: Japanese General Text Embeddings Ruri v3 is a general-purpose Japanese text embedding model built on top of ModernBERT-Ja. Ruri v3 offers several key technical advantages: - State-of-the-art performance for Japanese text embedding tasks. - Supports sequence lengths up to 8192 tokens - Previous versions of Ruri (v1, v2) were limited to 512. - Expanded vocabulary of 100K tokens, compared to 32K in v1 and v2 - The larger vocabulary make input sequences shorter, improving efficiency. - Integrated FlashAttention, following ModernBERT's architecture - Enables faster inference and fine-tuning. - Tokenizer based solely on SentencePiece - Unlike previous versions, which relied on Japanese-specific BERT tokenizers and required pre-tokenized input, Ruri v3 performs tokenization with SentencePiece only—no external word segmentation tool is required. Model Series We provide Ruri-v3 in several model sizes. Below is a summary of each model. Usage You can use our models directly with the transformers library v4.48.0 or higher: Additionally, if your GPUs support Flash Attention 2, we recommend using our models with Flash Attention 2. Then you can load this model and run inference. Benchmarks JMTEB Evaluated with JMTEB. Model Details Model Description - Model Type: Sentence Transformer - Base model: cl-nagoya/ruri-v3-pt-310m - Maximum Sequence Length: 8192 tokens - Output Dimensionality: 768 - Similarity Function: Cosine Similarity - Language: Japanese - License: Apache 2.0 - Paper: https://arxiv.org/abs/2409.07737 Full Model Architecture Citation License This model is published under the Apache License, Version 2.0.

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makercl-nagoya
TypeEmbedding models
Parameters (lead)315M
Context8k tokens
Variants1
Based oncl-nagoya/ruri-v3-pt-310m
Released2025-04-09
Popularity427k downloads / month
Likes82
LicenceOpen weights

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together — the basis of search and RAG.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
ruri-v3-310m315MBF16~0.7 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys ruri for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (ruri below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"ruri","input":"text to embed"}'

Details

Languages, data & research

Languages

ja

Trained / evaluated on

cl-nagoya/ruri-v3-dataset-ft

Tags

safetensors modernbert sentence-similarity feature-extraction ja dataset:cl-nagoya/ruri-v3-dataset-ft

Papers

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want ruri on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More embedding models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms