Instructions to use microsoft/tapex-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/tapex-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("table-question-answering", model="microsoft/tapex-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("microsoft/tapex-base") model = AutoModelForSeq2SeqLM.from_pretrained("microsoft/tapex-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
encoder-encoder -> encoder-decoder
In the [paper](https://arxiv.org/abs/2107.07653): `TA PE X is conceptually simple and easy to implement. In this paper, we regard the pre-training as a sequence generation task and employ an encoder-decoder model`efb1f2a
-
Adding generation config file(s)
85ba1ba
-
Update config.json
Qian Liu968109c -
Delete tokenizer.json
Qian Liuec98f1d -
Upload tokenizer_config.json
Qian Liud9f3aaa
-
Update README.md
96afae4
-
Upload config.json
Qian Liue88355e -
Upload config.json
Qian LiuKeep aligned with bart-base on forced_bos_token_id09df58c
-
Update README.md
Qian Liudf3358a
-
Upload config.json
Qian Liu74976ce -
Update activation dropout
Qian Liua1180b7
-
Upload merges.txt
Qian Liue195be4 -
Update README.md
Qian Liu4139cb0 -
Update Tapex README.md
Qian Liue81963a -
Upload pytorch_model.bin with git-lfs
Qian LiuUpdate tapex-base model pre-trained with 5 million SQL data.9a7c476 -
Upload config.json
Qian LiuAdd tapex-base config file (mostly from bart-base)b28b9c3 -
Upload tokenizer.json
Qian LiuReuse tokenizer from tapex-base.373c82f -
Upload vocab.json
Qian LiuMove vocab.json from `bart-base` to `tapex-base`3a9b5ab -
Update TAPEX-base README
Qian Liu1091084 -
Update README.md
f1fe839 -
initial commit
9736e4b