T

Tapex Large Finetuned Wtq

Developed by microsoft
TAPEX is a table pre-training model that learns via neural SQL executor, based on the BART architecture, specifically designed for table reasoning tasks.
Downloads 2,431
Release Time : 3/10/2022

Model Overview

TAPEX achieves table pre-training by learning a neural SQL executor on a synthetic corpus, aiming to endow existing models with table reasoning capabilities.

Model Features

Table Pre-training
Learns via neural SQL executor, equipping the model with powerful table reasoning capabilities.
BART-based Architecture
Combines the advantages of bidirectional encoder and autoregressive decoder, suitable for sequence-to-sequence tasks.
Complex Question Answering
Capable of handling complex queries and reasoning problems involving tabular data.

Model Capabilities

Table Question Answering
Table Reasoning
Complex Query Processing

Use Cases

Data Querying
Table Data Question Answering
Answers complex questions about table data, such as comparisons, calculations, and finding specific information.
Can accurately answer questions like 'In which year did Beijing host the Olympics?'
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase