https://github.com/oshizo/JapaneseEmbeddingTrain
https://github.com/oshizo/JapaneseEmbeddingTrain
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/oshizo/JapaneseEmbeddingTrain
- Owner: oshizo
- Created: 2023-01-10T12:12:23.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2023-01-10T12:46:40.000Z (about 2 years ago)
- Last Synced: 2024-06-17T11:32:29.311Z (8 months ago)
- Language: Jupyter Notebook
- Size: 15.6 KB
- Stars: 6
- Watchers: 1
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# JapaneseEmbeddingTrain
Jupyter notebook for training sentence-transformers models with JSNLI.
The training script is a slightly modified version of the [NLI example Sentence-transformers repository](https://github.com/UKPLab/sentence-transformers/blob/master/examples/training/nli/training_nli_v2.py).
## Trained Models
* [oshizo/sbert-jsnli-luke-japanese-base-lite](https://huggingface.co/oshizo/sbert-jsnli-luke-japanese-base-lite/)
* This model was trained 1 epoch on Google Colab Pro A100 and took approximately 40 minutes.
## Evaluation
* https://github.com/oshizo/JapaneseEmbeddingEval