update wikisql fine-tuned model link.

This commit is contained in:
SivilTaram 2021-08-30 16:05:29 +08:00
Родитель 7ac2b6ff4d
Коммит 3e346f7a42
1 изменённых файлов: 1 добавлений и 0 удалений

Просмотреть файл

@ -125,6 +125,7 @@ Model | Dev Acc | Test Acc | Dataset | Download Data | Download Model
---|---|----|----|----|----
`tapex.large.wtq` | 58.0 | 57.2 | WikiTableQuestions | [wtq.preprocessed.zip](https://github.com/microsoft/Table-Pretraining/releases/download/preprocessed-data/wtq.preprocessed.zip) | [tapex.large.wtq.tar.gz](https://github.com/microsoft/Table-Pretraining/releases/download/fine-tuned-model/tapex.large.wtq.tar.gz)
`tapex.large.sqa` | 70.7 | 74.0 | SQA | [sqa.preprocessed.zip](https://github.com/microsoft/Table-Pretraining/releases/download/preprocessed-data/sqa.preprocessed.zip) | [tapex.large.sqa.tar.gz](https://github.com/microsoft/Table-Pretraining/releases/download/fine-tuned-model/tapex.large.sqa.tar.gz)
`tapex.large.wikisql` | 89.3 | 89.2 | WikiSQL | [wikisql.preprocessed.zip](https://github.com/microsoft/Table-Pretraining/releases/download/preprocessed-data/wikisql.preprocessed.zip) | [tapex.large.wikisql.tar.gz](https://github.com/microsoft/Table-Pretraining/releases/download/fine-tuned-model/tapex.large.wikisql.tar.gz)
Given these fine-tuned model weights, you can play with them using the `predict` mode in `examples/tableqa/run_model.py`.