--- language: - ja - en license_name: sarahina-non-commercial-license license_link: LICENSE tags: - transformers - sentence-similarity - feature-extraction - sentence-transformers pipeline_tag: sentence-similarity inference: false datasets: - hpprc/emb - cl-nagoya/auto-wiki-qa - cl-nagoya/ruri-dataset-ft - hpprc/mqa-ja - izumi-lab/llm-japanese-dataset - sentence-transformers/NQ-retrieval - sbintuitions/JSQuAD - SkelterLabsInc/JaQuAD - wikimedia/wikipedia - cl-nagoya/nu-mnli - castorini/mr-tydi --- # Sarashina-Embedding-v1-1B **[日本語のREADME/Japanese README](https://huggingface.co/sbintuitions/sarashina-embedding-v1-1b/blob/main/README_JA.md)** "Sarashina-Embedding-v1-1B" is a Japanese text embedding model, based on the 1.2B-parameter Japansese LLM "[Sarashina2.1-1B](https://huggingface.co/sbintuitions/sarashina2.1-1b)". We trained this model with multi-stage contrastive learning. We achieved the state-of-the-art average score in the average of 16 datasets in [JMTEB](https://huggingface.co/datasets/sbintuitions/JMTEB) (Japanese Massive Text Embedding Benchmark). This model maps sentences & paragraphs to a 1792-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [Sarashina2.1-1B](https://huggingface.co/sbintuitions/sarashina2.1-1b) - **Maximum Sequence Length:** 8,192 tokens - **Output Dimensionality:** 1,792 dimensions - **Similarity Function:** Cosine Similarity - **Language:** Japanese - **License:** [Sarashina Model NonCommercial License Agreement](https://huggingface.co/sbintuitions/sarashina-embedding-v1-1b/blob/main/LICENSE) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: LlamaModel (1): Pooling({'word_embedding_dimension': 1792, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, 'include_prompt': False}) ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("sbintuitions/sarashina-embedding-v1-1b") # Run inference sentences = [ '更級日記は、平安時代中期に菅原孝標女によって書かれた回想録です。', 'Sarashinaは、SB Intuitionsが開発した日本語大規模言語モデルです。これまでに7B, 13B, 70B, 8x70Bのモデルが公開されています。', '更科蕎麦とはなんですか?' ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 1792] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` **Note** - You do not need to add prefixes such as "Query: " and "Document: " at the beginning of the input sentence. - This model is licensed under the [Sarashina Model NonCommercial License Agreement](https://huggingface.co/sbintuitions/sarashina-embedding-v1-1b/blob/main/LICENSE), which has restrictions on commercial use. If you are interested in utilizing this model for your business, please feel free to contact us through our [contact page](https://www.sbintuitions.co.jp/#contact). ## Training "Sarashina-Embedding-v1-1B" is created through the following two-stage learning process: ### Stage 1: Weakly-supervised Learning To achieve generic text embedding performance across a wide range of domains, we performed contrastive training on weakly-supervised data consisting of our own web-crawled data and open data. #### Datasets |dataset|counts| |:-:|:-:| |[AutoWikiQA](https://huggingface.co/datasets/cl-nagoya/auto-wiki-qa)|50,521,135| |web-crawled data (ours)|47,370,649| |[MQA](https://huggingface.co/datasets/hpprc/mqa-ja)|12,941,472| |[llm-japanese-dataset](https://huggingface.co/datasets/izumi-lab/llm-japanese-dataset)|9,074,340| |[Wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia)|5,555,212| |Quiz dataset (ours)|988,478| |[Natural Questions](https://huggingface.co/datasets/sentence-transformers/NQ-retrieval)|132,796| |[JSQuAD](https://huggingface.co/datasets/sbintuitions/JSQuAD)|62,859| |[SNOW(T15+T23)](https://aclanthology.org/L18-1185)|62,758| |[JaQuAD](https://huggingface.co/datasets/SkelterLabsInc/JaQuAD)|31,746| |[MKQA](https://aclanthology.org/2021.tacl-1.82)|3,318| ||| |**total**|**126,744,763**| ### Step2: Supervised Fine-tuning To enable the model to learn a more accurate query-document similarity, we performed supervised fine-tuning using the following datasets. #### Datasets |dataset|counts| |:-:|:-:| |[JSNLI](https://nlp.ist.i.kyoto-u.ac.jp/?%E6%97%A5%E6%9C%AC%E8%AA%9ESNLI%28JSNLI%29%E3%83%87%E3%83%BC%E3%82%BF%E3%82%BB%E3%83%83%E3%83%88)|141,388 | |[NU-MNLI](https://huggingface.co/datasets/cl-nagoya/nu-mnli)|67,987| |[Mr. TyDi](https://huggingface.co/datasets/castorini/mr-tydi) (only Japanese subset)| 3,697 | |[Natural Questions](https://huggingface.co/datasets/sentence-transformers/NQ-retrieval) (sampled)| 20,000| ||| |**total**|**233,072**| # Evaluation Results with [JMTEB](https://huggingface.co/datasets/sbintuitions/JMTEB) Model |Max Tokens|Avg. | Retrieval | STS | Classification | Reranking | Clustering | PairClassification | |:----------------------------------------------|:----------|:----------|:------------|:----------|:-----------------|:------------|:-------------|:---------------------| | [OpenAI/text-embedding-3-large](https://openai.com/index/new-embedding-models-and-api-updates/)[^oai] | 8191 |74.05 | 74.48 | 82.52 | 77.58 | 93.58 | 53.32 | 62.35 | | [cl-nagoya/ruri-large](https://arxiv.org/abs/2409.07737) | 512 |73.31 | 73.02 | **83.13** | 77.43 | 92.99 | 51.82 | 62.29 | | [pkshatech/GLuCoSE-base-ja-v2](https://huggingface.co/pkshatech/GLuCoSE-base-ja-v2) | 512 |72.23 | 73.36 | 82.96 | 74.21 | 93.01 | 48.65 | **62.37** | | [pkshatech/RoSEtta-base-ja](https://huggingface.co/pkshatech/RoSEtta-base-ja) |1024 |72.04 | 73.21 | 81.39 | 72.41 | 92.69 | 53.23 | 61.74 | | [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) | 512|70.90 | 70.98 | 79.70 | 72.89 | 92.96 | 51.24 | 62.15 | ||| |[**Sarashina-Embedding-v1-1B**](https://huggingface.co/sbintuitions/sarashina-embedding-v1-1b)(This model)|**8192**|**75.50**|**77.61**|82.71|**78.37**|**93.74**|**53.86**|62.00| ## License This model is licensed under [Sarashina Model NonCommercial License Agreement](https://huggingface.co/sbintuitions/sarashina-embedding-v1-1b/blob/main/LICENSE). **If you are interested in using this model for commercial purposes, please feel free to contact us through our [contact page](https://www.sbintuitions.co.jp/#contact).**