import torch.nn.functional as F
from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("cl-nagoya/ruri-large")

# Don't forget to add the prefix "クエリ: " for query-side or "文章: " for passage-side texts.
sentences = [
    "クエリ: 瑠璃色はどんな色？",
    "文章: 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]。",
    "クエリ: ワシやタカのように、鋭いくちばしと爪を持った大型の鳥類を総称して「何類」というでしょう?",
    "文章: ワシ、タカ、ハゲワシ、ハヤブサ、コンドル、フクロウが代表的である。これらの猛禽類はリンネ前後の時代(17~18世紀)には鷲類・鷹類・隼類及び梟類に分類された。ちなみにリンネは狩りをする鳥を単一の目(もく)にまとめ、vultur(コンドル、ハゲワシ)、falco(ワシ、タカ、ハヤブサなど)、strix(フクロウ)、lanius(モズ)の4属を含めている。",
]

embeddings = model.encode(sentences, convert_to_tensor=True)
print(embeddings.size())
# [4, 1024]

similarities = F.cosine_similarity(embeddings.unsqueeze(0), embeddings.unsqueeze(1), dim=2)
print(similarities)
# [[1.0000, 0.9429, 0.6565, 0.6997],
#  [0.9429, 1.0000, 0.6579, 0.6768],
#  [0.6565, 0.6579, 1.0000, 0.8933],
#  [0.6997, 0.6768, 0.8933, 1.0000]]

Benchmarks

JMTEB

Evaluated with JMTEB.

Model	#Param.	Avg.	Retrieval	STS	Classfification	Reranking	Clustering	PairClassification
cl-nagoya/sup-simcse-ja-base	111M	68.56	49.64	82.05	73.47	91.83	51.79	62.57
cl-nagoya/sup-simcse-ja-large	337M	66.51	37.62	83.18	73.73	91.48	50.56	62.51
cl-nagoya/unsup-simcse-ja-base	111M	65.07	40.23	78.72	73.07	91.16	44.77	62.44
cl-nagoya/unsup-simcse-ja-large	337M	66.27	40.53	80.56	74.66	90.95	48.41	62.49
pkshatech/GLuCoSE-base-ja	133M	70.44	59.02	78.71	76.82	91.90	49.78	66.39

sentence-transformers/LaBSE	472M	64.70	40.12	76.56	72.66	91.63	44.88	62.33
intfloat/multilingual-e5-small	118M	69.52	67.27	80.07	67.62	93.03	46.91	62.19
intfloat/multilingual-e5-base	278M	70.12	68.21	79.84	69.30	92.85	48.26	62.26
intfloat/multilingual-e5-large	560M	71.65	70.98	79.70	72.89	92.96	51.24	62.15

OpenAI/text-embedding-ada-002	-	69.48	64.38	79.02	69.75	93.04	48.30	62.40
OpenAI/text-embedding-3-small	-	70.86	66.39	79.46	73.06	92.92	51.06	62.27
OpenAI/text-embedding-3-large	-	73.97	74.48	82.52	77.58	93.58	53.32	62.35

Ruri-Small	68M	71.53	69.41	82.79	76.22	93.00	51.19	62.11
Ruri-Base	111M	71.91	69.82	82.87	75.58	92.91	54.16	62.38
Ruri-Large (this model)	337M	73.31	73.02	83.13	77.43	92.99	51.82	62.29

Model Details

Model Description

Model Type: Sentence Transformer
Base model: cl-nagoya/ruri-pt-large
Maximum Sequence Length: 512 tokens
Output Dimensionality: 1024
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': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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})
)

Framework Versions

Python: 3.10.13
Sentence Transformers: 3.0.0
Transformers: 4.41.2
PyTorch: 2.3.1+cu118
Accelerate: 0.30.1
Datasets: 2.19.1
Tokenizers: 0.19.1

Citation

bibtex

@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.