Skip to main content

Transformers kit - Multi-task QA/Tagging/Multi-label Multi-Class Classification/Generation with BERT/ALBERT/T5/BERT

Project description

PyPI Download Build Last Commit CodeFactor Visitor

What is it

TFKit is a deep natural language process framework for classification/tagging/question answering/embedding study and language generation.
It leverages the use of transformers on many tasks with different models in this all-in-one framework.
All you need is a little change of config.

Task Supported

With transformer models - BERT/ALBERT/T5/BART......

Classification :label: multi-class and multi-label classification
Question Answering :page_with_curl: extractive qa
Question Answering :radio_button: multiple-choice qa
Tagging :eye_speech_bubble: sequence level tagging / sequence level with crf
Text Generation :memo: seq2seq language model
Text Generation :pen: causal language model
Text Generation :printer: once generation model / once generation model with ctc loss
Text Generation :pencil: onebyone generation model
Self-supervise Learning :diving_mask: mask language model

Getting Started

Learn more from the document.

How To Use

Step 0: Install

Simple installation from PyPI

pip install tfkit

Step 1: Prepare dataset in csv format

Task format

input, target

Step 2: Train model

tfkit-train \
--model clas \
--config xlm-roberta-base \
--train training_data.csv \
--test testing_data.csv \
--lr 4e-5 \
--maxlen 384 \
--epoch 10 \
--savedir roberta_sentiment_classificer

Step 3: Evaluate

tfkit-eval \
--model roberta_sentiment_classificer/ \
--metric clas \
--valid testing_data.csv

Advanced features

Multi-task training
tfkit-train \
  --model clas clas \
  --config xlm-roberta-base \
  --train training_data_taskA.csv training_data_taskB.csv \
  --test testing_data_taskA.csv testing_data_taskB.csv \
  --lr 4e-5 \
  --maxlen 384 \
  --epoch 10 \
  --savedir roberta_sentiment_classificer_multi_task



Thanks for your interest.There are many ways to contribute to this project. Get started here.

License PyPI - License

Icons reference

Icons modify from Freepik from
Icons modify from Nikita Golubev from

Project details

Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tfkit-0.8.1.tar.gz (220.3 kB view hashes)

Uploaded source

Built Distributions

tfkit-0.8.1-py3.7.egg (195.7 kB view hashes)

Uploaded 3 7

tfkit-0.8.1-py3-none-any.whl (85.1 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page