Model reference · open weights
transformers-ud-japanese-electra-ginza-510 is an open-weight embedding model from megagonlabs. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | megagonlabs |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Context | 512 tokens |
| Runs with | transformers |
| Released | 2022-03-02 |
| Popularity | 15k downloads / month |
| Licence | Open weights |
About
This is an ELECTRA model pretrained on approximately 200M Japanese sentences extracted from the mC4 and finetuned by spaCy v3 on UD_Japanese_BCCWJ r2.8.
The base pretrain model is megagonlabs/transformers-ud-japanese-electra-base-discrimininator.
The entire spaCy v3 model is distributed as a python package named ja_ginza_electra from PyPI along with GiNZA v5 which provides some custom pipeline components to recognize the Japanese bunsetu-phrase structures.
Try running it as below:
$ pip install ginza ja_ginza_electra
$ ginza
The models are distributed under the terms of the MIT License.
This model is permitted to be published under the MIT License under a joint research agreement between NINJAL (National Institute for Japanese Language and Linguistics) and Megagon Labs Tokyo.
Contains information from mC4 which is made available under the ODC Attribution License.
@article{2019t5,
author = {Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu},
title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer},
journal = {arXiv e-prints},
year = {2019},
archivePrefix = {arXiv},
eprint = {1910.10683},
}
Asahara, M., Kanayama, H., Tanaka, T., Miyao, Y., Uematsu, S., Mori, S.,
Matsumoto, Y., Omura, M., & Murawaki, Y. (2018).
Universal Dependencies Version 2 for Japanese.
In LREC-2018.
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys transformers-ud-japanese-electra-ginza-510 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (transformers-ud-japanese-electra-ginza-510 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":"transformers-ud-japanese-electra-ginza-510","input":"text to embed"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.