tapex large finetuned wtq

提供商microsoft
分类table-question-answering
许可证mit
下载量194
星标0

简介

TAPEX-Large-Finetuned-WTQ 是微软推出的专门针对表格问答（Table QA）优化的预训练模型。与通用 LLM 不同，它通过在海量表格数据上进行预训练，能够更精准地理解行列关系和单元格语义，特别是在处理需要复杂推理的 WikiTableQuestions (WTQ) 任务时表现出色。对于开发者而言，它是一个理想的轻量化垂直方案，无需依赖昂贵的 GPT-4 即可实现高质量的表格数据检索与分析，上手难度较低，可直接集成到企业内部的报表分析或知识库系统中。

核心亮点

  • 深耕表格语义，复杂行列推理能力强
  • 针对 WTQ 数据集微调，问答精度高
  • MIT 协议开源，企业集成部署成本低
  • 垂直领域替代方案，无需依赖通用大模型

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

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

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download microsoft/tapex-large-finetuned-wtq

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例） 
huggingface-cli download microsoft/tapex-large-finetuned-wtq config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

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

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/microsoft/tapex-large-finetuned-wtq

如果您希望跳过 lfs 大文件下载，可以使用如下命令

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

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

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

模型下载

我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 ModelScope：

操作指引 
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库 
modelscope download --model microsoft/tapex-large-finetuned-wtq

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例）

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例） 
modelscope download --model microsoft/tapex-large-finetuned-wtq README.md --local_dir ./dir

更多更丰富的命令行下载选项，可参见具体文档

SDK 下载

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

Git 下载

请确保 lfs 已经被正确安装

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

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/microsoft/tapex-large-finetuned-wtq.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 快速开发

下载并安装 ModelScope library

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

模型加载和推理

模型加载和推理 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

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

完整文档

来源: HuggingFace

---
language: en
tags:

  • tapex

  • table-question-answering

datasets:
  • wikitablequestions

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

This model is the tapex-base model fine-tuned on the WikiTableQuestions dataset.

Intended Uses

You can use the model for table question answering on *complex* questions. Some solveable questions are shown below (corresponding tables now shown):

| Question | Answer |
|:---: |:---:|
| according to the table, what is the last title that spicy horse produced? | Akaneiro: Demon Hunters |
| what is the difference in runners-up from coleraine academical institution and royal school dungannon? | 20 |
| what were the first and last movies greenstreet acted in? | The Maltese Falcon, Malaya |
| in which olympic games did arasay thondike not finish in the top 20? | 2012 |
| which broadcaster hosted 3 titles but they had only 1 episode? | Channel 4 |

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-large-finetuned-wtq")
model = BartForConditionalGeneration.from_pretrained("microsoft/tapex-large-finetuned-wtq")


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 = "In which year did beijing host the Olympic Games?"
encoding = tokenizer(table=table, query=query, return_tensors="pt")

outputs = model.generate(**encoding)


print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
[' 2008.0']

How to Eval

Please find the eval 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}
}
查看官方来源