SAVRN
Search Contact SAVRN

SAVRN Model Hub · Models by Task

Table Question Answering Models

1 open-weight table question answering models in the SAVRN Model Hub, with Microsoft publishing the most.

1Models
1Publishers
1Licenses

Most Downloaded

ModelPublisherParametersLicenseMonthly downloadsCheapest GPUs at 16-bit
tapex-base-finetuned-wikisql Microsoft mit 812.2k

Licenses

LicenseModelsCommercial use
mit1Yes

Who Publishes Them

PublisherModels
Microsoft1

All 1 Models

Model · Table question answering

tapex-base-finetuned-wikisql

Microsoft

TAPEX was proposed in TAPEX: Table Pre-training via Learning a Neural SQL Executor by Qian Liu, Bei Chen, Jiaqi Guo, Morteza Ziyadi, Zeqi Lin, Weizhu Chen, Jian-Guang Lou. The original repo can be found here. TAPEX (Table Pre-training via Execution) is a conceptually simple and empirically powerful pre-training approach to empower existing models with table reasoning skills. TAPEX realizes table pre-training by learning a neural SQL executor over a synthetic corpus, which is obtained by automatically synthesizing executable SQL queries. TAPEX is based on the BART architecture, the transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive…

Open weights mit 1,024 tokens transformers

Questions

Which Table question answering models are most downloaded?

By monthly downloads reported by the Hugging Face Hub: tapex-base-finetuned-wikisql (812.2k).

Other Tasks

See all