| --- |
| inference: false |
| datasets: |
| - miracl/miracl |
| - answerdotai/MMARCO-japanese-32-scored-triplets |
| - hotchpotch/JQaRA |
| - matsuxr/JaGovFaqs-22k |
| - unicamp-dl/mmarco |
| language: |
| - ja |
| pipeline_tag: sentence-similarity |
| tags: |
| - ColBERT |
| - multi-vector |
| - sentence-transformers |
| base_model: |
| - cl-tohoku/bert-base-japanese-v3 |
| - bclavie/JaColBERT |
| license: mit |
| library_name: RAGatouille |
| --- |
| |
| Model weights for the final JaColBERTv2.5 checkpoint, using an entirely overhauled training recipe and trained on just 40% of the data of JaColBERTv2. |
|
|
| This model largely outperforms all previous approaches, including JaColBERTV2 multilingual models such as BGE-M3, on all datasets. |
|
|
| This page will be updated with the full details and the model report in the next few days. |
|
|
|
|
| ## Sentence Transformers |
|
|
| As of [Sentence Transformers](https://www.sbert.net/) v6.0.0, this model can also be loaded directly as a multi-vector (ColBERT-style late interaction) retriever via the `MultiVectorEncoder`: |
|
|
| ```bash |
| pip install "sentence-transformers>=6.0.0" fugashi unidic-lite |
| ``` |
|
|
| ```python |
| from sentence_transformers import MultiVectorEncoder |
| |
| model = MultiVectorEncoder("answerdotai/JaColBERTv2.5") |
| |
| query = "日本で一番高い山は何ですか？" |
| documents = [ |
| "富士山は日本で最も高い山で、標高は3776メートルです。", |
| "東京は日本の首都で、世界最大の都市圏の一つです。", |
| "北岳は南アルプスにある山で、日本で二番目に高い山です。", |
| "富士山は静岡県と山梨県にまたがる活火山です。", |
| ] |
| |
| query_embeddings = model.encode_query(query) |
| document_embeddings = model.encode_document(documents) |
| print(query_embeddings.shape, document_embeddings[0].shape) |
| # torch.Size([32, 128]) torch.Size([21, 128]) |
| |
| # MaxSim late-interaction scoring (higher is more relevant) |
| scores = model.similarity(query_embeddings, document_embeddings) |
| print(scores) |
| # tensor([[30.6709, 28.9073, 29.6979, 29.0785]], device='cuda:0') |
| ``` |
|
|
|
|
| ``` |
| @misc{clavié2024jacolbertv25optimisingmultivectorretrievers, |
| title={JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources}, |
| author={Benjamin Clavié}, |
| year={2024}, |
| eprint={2407.20750}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.IR}, |
| url={https://arxiv.org/abs/2407.20750}, |
| } |
| ``` |
