Japanese NLP sample codes
Перейти к файлу
konabuta db09441191
Merge pull request #11 from Azure/bert-train
BERT Fine Tuning Example
2021-10-19 23:45:33 +09:00
.devcontainer devcontainer 2021-08-19 01:20:48 +00:00
.github/workflows Update rinna-mlops.yml 2021-08-24 13:13:29 +09:00
examples modified data folder path 2021-10-19 14:27:52 +00:00
.gitignore Add cache dirs 2021-08-17 08:54:50 +00:00
CODE_OF_CONDUCT.md CODE_OF_CONDUCT.md committed 2021-07-20 22:07:08 -07:00
LICENSE LICENSE committed 2021-07-20 22:07:09 -07:00
NOTICE.md init 2021-07-21 12:44:41 +00:00
README.md bert-train fine tune#2 2021-10-13 13:52:33 +00:00
SECURITY.md SECURITY.md committed 2021-07-20 22:07:10 -07:00
SUPPORT.md init 2021-07-27 07:24:22 +00:00
cgmanifest.json init 2021-07-21 12:44:41 +00:00

README.md

NLP Samples

This repo is a collection of NLP samples on Azure, especially for Japanese.

Examples

scenario description
rinna GPT-2 train Fine-Tune rinna GPT-2 model with ONNX Runtime
rinna GPT-2 predict Convert rinna GPT-2 Model to ONNX with Quantization
BERT Fine Tuning BERT Train Fine Tuning

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.