tapex base
简介
核心亮点
- 深耕表格语义，处理结构化数据比通用模型更精准
- 支持复杂表格推理，无需繁琐的 Prompt 工程
- MIT 协议开源，部署灵活且推理成本远低于大模型
- 适用于自动化报表分析及企业知识库表格问答
使用方法
# 安装 Hugging Face transformers
pip install transformers torch# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("microsoft/tapex-base")
tokenizer = AutoTokenizer.from_pretrained("microsoft/tapex-base")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：
pip install -U huggingface_hub命令行下载
下载完整模型库
huggingface-cli download microsoft/tapex-base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-base config.json --local-dir ./dirSDK 下载
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('microsoft/tapex-base')Git 下载
请确保 lfs 已经被正确安装
git lfs install
git clone https://huggingface.co/microsoft/tapex-base如果您希望跳过 lfs 大文件下载，可以使用如下命令
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/microsoft/tapex-base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
pip install -U transformers torch模型加载和推理
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained('microsoft/tapex-base')
tokenizer = AutoTokenizer.from_pretrained('microsoft/tapex-base')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：
pip install modelscope命令行下载
下载完整模型库
modelscope download --model microsoft/tapex-base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-base README.md --local_dir ./dirSDK 下载
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('microsoft/tapex-base')Git 下载
请确保 lfs 已经被正确安装
git lfs install
git clone https://www.modelscope.cn/microsoft/tapex-base.git如果您希望跳过 lfs 大文件下载，可以使用如下命令
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/microsoft/tapex-base.gitModelScope 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
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
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
p = pipeline('text-generation', 'microsoft/tapex-base')完整文档
---
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:
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
@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}
}