TAPEX (Table Pre-training via Learning a Neural SQL Executor) Large Finetuned Model
A large-sized TAPEX model fine-tuned on the WikiTableQuestions dataset, designed to enhance performance in table-based question answering tasks.
About Model
The TAPEX Large Fine-Tuned on WikiTableQuestions (WTQ) model builds upon the TAPEX architecture, specifically fine-tuned to excel in answering complex questions based on tabular data. Leveraging the WikiTableQuestions dataset, which comprises intricate questions paired with semi-structured tables, this model has been trained to interpret and reason over tables to generate accurate responses. The fine-tuning process involves adapting the pre-trained TAPEX model to understand the nuances of the dataset, enabling it to handle a variety of table structures and question formats effectively. This model is particularly beneficial for applications requiring precise data extraction and reasoning over tables, such as data analysis, report generation, and automated insights from structured data sources.
TAPEX (Table Pre-training via Learning a Neural SQL Executor) Large Finetuned Model
Metadata
MIT
Qian Liu and Bei Chen and Jiaqi Guo and Morteza Ziyadi and Zeqi Lin and Weizhu Chen and Jian-Guang Lou
Fine-Tuned Model
N.A.
Open
Sector Agnostic
12/03/25 06:34:43
0
Activity Overview
0
2 
132 
0
Tags
- TableQuestionAnswering
- TAPEX
- WikiTableQuestions
- FineTunedModel
- DataExtraction
- BART
- Transformers
- NaturalLanguageProcessing
License Control
MIT
More Models from Microsoft Corporation (India) Pvt. Ltd.
- 0
- 6
- 0
173
- 0
- 5
- 0
- 132
- 0
- 5
- 0
- 99
- 0
- 2
- 0
- 133
- 0
- 3
- 0
- 93
- 0
- 3
- 0
- 121
- 0
- 5
- 0
- 106
- 0
- 4
- 0
- 95
- 0
- 5
- 0
- 138
- 0
- 87
- 0
- 1,252
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.