cl-nagoya/ruri-v3-310m
82491k
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:
pip install -U "transformers>=4.48.0" sentence-transformersAdditionally, if your GPUs support Flash Attention 2, we recommend using our models with Flash Attention 2.
pip install flash-attn --no-build-isolationThen you can load this model and run inference.
import torch
import torch.nn.functional as F
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
device = "cuda" if torch.cuda.is_available() else "cpu"
model = SentenceTransformer("cl-nagoya/ruri-v3-310m", device=device)
# Ruri v3 employs a 1+3 prefix scheme to distinguish between different types of text inputs:
# "" (empty string) is used for encoding semantic meaning.
# "トピック: " is used for classification, clustering, and encoding topical information.
# "検索クエリ: " is used for queries in retrieval tasks.
# "検索文書: " is used for documents to be retrieved.
sentences = [
"川べりでサーフボードを持った人たちがいます",
"サーファーたちが川べりに立っています",
"トピック: 瑠璃色のサーファー",
"検索クエリ: 瑠璃色はどんな色？",
"検索文書: 瑠璃色（るりいろ）は、紫みを帯びた濃い青。名は、半貴石の瑠璃（ラピスラズリ、英: lapis lazuli）による。JIS慣用色名では「こい紫みの青」（略号 dp-pB）と定義している[1][2]。",
]
embeddings = model.encode(sentences, convert_to_tensor=True)
print(embeddings.size())
# [5, 768]
similarities = F.cosine_similarity(embeddings.unsqueeze(0), embeddings.unsqueeze(1), dim=2)
print(similarities)
# [[1.0000, 0.9603, 0.8157, 0.7074, 0.6916],
# [0.9603, 1.0000, 0.8192, 0.7014, 0.6819],
# [0.8157, 0.8192, 1.0000, 0.8701, 0.8470],
# [0.7074, 0.7014, 0.8701, 1.0000, 0.9746],
# [0.6916, 0.6819, 0.8470, 0.9746, 1.0000]]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
SentenceTransformer(
(0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)Citation
@misc{
Ruri,
title={{Ruri: Japanese General Text Embeddings}},
author={Hayato Tsukagoshi and Ryohei Sasano},
year={2024},
eprint={2409.07737},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2409.07737},
}License
This model is published under the Apache License, Version 2.0.