tapex large

Providermicrosoft
Categorytable-question-answering
Licensemit
Downloads168
Stars0

Overview

TAPEX-Large is a specialized transformer model engineered specifically for table-based question answering. Unlike general-purpose LLMs that often struggle with structured data alignment, TAPEX is pre-trained on tabular corpora to understand the relational dynamics between rows and columns. For developers, this means higher accuracy in complex data retrieval tasks—such as aggregations or multi-hop reasoning—without the need for extensive prompt engineering. It integrates well into data pipelines where structured query generation or natural language interfaces for databases are required, offering a more predictable and computationally efficient alternative to massive general models for table-specific workloads.

Highlights

  • Optimized for structured table-question answering tasks
  • Superior reasoning over relational data and cell values
  • MIT licensed for flexible commercial integration
  • Reduced hallucination compared to general-purpose LLMs

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("microsoft/tapex-large")
tokenizer = AutoTokenizer.from_pretrained("microsoft/tapex-large")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download microsoft/tapex-large

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download microsoft/tapex-large config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('microsoft/tapex-large')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/microsoft/tapex-large

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/microsoft/tapex-large

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('microsoft/tapex-large')
tokenizer = AutoTokenizer.from_pretrained('microsoft/tapex-large')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance 
pip install modelscope

CLI Download

Download the full repository

Download the full repository 
modelscope download --model microsoft/tapex-large

Download a single file to a local folder (e.g. README.md into ./dir)

Download a single file to a local folder (e.g. README.md into ./dir) 
modelscope download --model microsoft/tapex-large README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('microsoft/tapex-large')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://www.modelscope.cn/microsoft/tapex-large.git

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/microsoft/tapex-large.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

Install the ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

Load the model and run inference 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'microsoft/tapex-large')

Full Documentation

来源: HuggingFace

---
language: en
tags:

  • tapex

  • table-question-answering

license: mit
---

TAPEX (large-sized model)

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.

Model description

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 (GPT-like) decoder.

Intended Uses

⚠️ This model checkpoint is ONLY used for fine-tuining on downstream tasks, and you CANNOT use this model for simulating neural SQL execution, i.e., employ TAPEX to execute a SQL query on a given table. The one that can neurally execute SQL queries is at here.
> This separation of two models for two kinds of intention is because of a known issue in BART large, and we recommend readers to see this comment for more details.

How to Fine-tuning

Please find the fine-tuning script here.

BibTeX entry and citation info

bibtex
@inproceedings{
    liu2022tapex,
    title={{TAPEX}: Table Pre-training via Learning a Neural {SQL} Executor},
    author={Qian Liu and Bei Chen and Jiaqi Guo and Morteza Ziyadi and Zeqi Lin and Weizhu Chen and Jian-Guang Lou},
    booktitle={International Conference on Learning Representations},
    year={2022},
    url={https://openreview.net/forum?id=O50443AsCP}
}
View official source
Join our Telegram