tapex base

Providermicrosoft
Categorytable-question-answering
Licensemit
Downloads205
Stars0

Overview

TAPEX Base is a specialized transformer model engineered specifically for table-question answering. Unlike general-purpose LLMs that often struggle with structured data alignment, TAPEX is pretrained on tabular data to understand the relationship between cell values and their corresponding headers. This makes it highly effective for complex reasoning tasks over tables, such as aggregation, filtering, and multi-hop retrieval. For developers, it offers a more lightweight and deterministic alternative to massive generative models when building data-driven dashboards or automated reporting tools. Integration is straightforward via the Hugging Face ecosystem, allowing it to be dropped into existing NLP pipelines for high-accuracy table parsing without the overhead of extensive prompt engineering.

Highlights

  • Optimized for structured table-question answering tasks
  • Deep understanding of tabular data relationships
  • Lightweight alternative to general-purpose LLMs
  • Seamless integration via Hugging Face transformers
  • Permissive MIT license for commercial deployment

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-base")
tokenizer = AutoTokenizer.from_pretrained("microsoft/tapex-base")

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-base

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-base 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-base')

Git Download

Make sure git-lfs is installed first

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

To skip LFS large-file downloads, use:

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

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-base')
tokenizer = AutoTokenizer.from_pretrained('microsoft/tapex-base')

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-base

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-base 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-base')

Git Download

Make sure git-lfs is installed first

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

To skip LFS large-file downloads, use:

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

Full Documentation

来源: HuggingFace

---
language: en
tags:

  • tapex

  • table-question-answering

license: mit
---

TAPEX (base-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-decoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder.

Intended Uses

You can use the raw model for simulating neural SQL execution, i.e., employ TAPEX to execute a SQL query on a given table. However, the model is mostly meant to be fine-tuned on a supervised dataset. Currently TAPEX can be fine-tuned to tackle table question answering tasks and table fact verification tasks. See the model hub to look for fine-tuned versions on a task that interests you.

How to Use

Here is how to use this model in transformers:

python
from transformers import TapexTokenizer, BartForConditionalGeneration
import pandas as pd

tokenizer = TapexTokenizer.from_pretrained("microsoft/tapex-base")
model = BartForConditionalGeneration.from_pretrained("microsoft/tapex-base")


data = {
    "year": [1896, 1900, 1904, 2004, 2008, 2012],
    "city": ["athens", "paris", "st. louis", "athens", "beijing", "london"]
}
table = pd.DataFrame.from_dict(data)


tapex accepts uncased input since it is pre-trained on the uncased corpus

query = "select year where city = beijing"
encoding = tokenizer(table=table, query=query, return_tensors="pt")

outputs = model.generate(**encoding)


print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
['2008']

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