Skip to main content

Transformers kit - NLP library for different downstream tasks, built on huggingface project

Project description




PyPI Download Build Last Commit

TFKit lets everyone make use of transformer architecture on many tasks and models in small change of config.
At the same time, it can do multi-task multi-model learning, and can introduce its own data sets and tasks through simple modifications.

Feature

  • One-click replacement of different pre-trained models
  • Support multi-model and multi-task
  • Classifier with multiple labels and multiple classifications
  • Unify input formats for different tasks
  • Separation of data reading and model architecture
  • Support various loss function and indicators

Supplement

  • Model list: Support Bert/GPT/GPT2/XLM/XLNet/RoBERTa/CTRL/ALBert/...
  • NLPrep: download and preprocessing data in one line
  • nlp2go: create demo api as quickly as possible.

Quick Start

Installing via pip

pip install tfkit

Running TFKit to train a ner model

download dataset using nlprep

nlprep --dataset tag_clner  --outdir ./clner_row --util s2t

train model with albert

tfkit-train --batch 10 \
--epoch 5 \
--lr 5e-5 \
--train ./clner_row/train \
--test ./clner_row/test \
--maxlen 512 \
--model tagRow \
--savedir ./albert_ner \
--config voidful/albert_chinese_small

eval model

tfkit-eval --model ./albert_ner/3.pt --valid ./clner_row/validation --metric clas

result

Task : default report 
TASK:  default 0
                precision    recall  f1-score   support

    B_Abstract       0.00      0.00      0.00         1
    B_Location       1.00      1.00      1.00         1
      B_Metric       1.00      1.00      1.00         1
B_Organization       0.00      0.00      0.00         1
      B_Person       1.00      1.00      1.00         1
    B_Physical       0.00      0.00      0.00         1
       B_Thing       1.00      1.00      1.00         1
        B_Time       1.00      1.00      1.00         1
    I_Abstract       1.00      1.00      1.00         1
    I_Location       1.00      1.00      1.00         1
      I_Metric       1.00      1.00      1.00         1
I_Organization       0.00      0.00      0.00         1
      I_Person       1.00      1.00      1.00         1
    I_Physical       0.00      0.00      0.00         1
       I_Thing       1.00      1.00      1.00         1
        I_Time       1.00      1.00      1.00         1
             O       1.00      1.00      1.00         1

     micro avg       1.00      0.71      0.83        17
     macro avg       0.71      0.71      0.71        17
  weighted avg       0.71      0.71      0.71        17
   samples avg       1.00      0.71      0.83        17

host prediction service

nlp2go --model ./albert_ner/3.pt --api_path ner

Overview

Train

$ tfkit-train
Run training

arguments:
  --train TRAIN [TRAIN ...]     train dataset path
  --test TEST [TEST ...]        test dataset path
  --config CONFIG               distilbert-base-multilingual-cased/bert-base-multilingual-cased/voidful/albert_chinese_small
  --model {once,twice,onebyone,clas,tagRow,tagCol,qa,onebyone-neg,onebyone-pos,onebyone-both} [{once,twice,onebyone,clas,tagRow,tagCol,qa,onebyone-neg,onebyone-pos,onebyone-both} ...]
                                model task
  --savedir SAVEDIR     model saving dir, default /checkpoints
optional arguments:
  -h, --help            show this help message and exit
  --batch BATCH         batch size, default 20
  --lr LR [LR ...]      learning rate, default 5e-5
  --epoch EPOCH         epoch, default 10
  --maxlen MAXLEN       max tokenized sequence length, default 368
  --lossdrop            loss dropping for text generation
  --tag TAG [TAG ...]   tag to identity task in multi-task
  --seed SEED           random seed, default 609
  --worker WORKER       number of worker on pre-processing, default 8
  --grad_accum          gradient accumulation, default 1
  --tensorboard         Turn on tensorboard graphing
  --resume RESUME       resume training
  --cache               cache training data

Eval

$ tfkit-eval
Run evaluation on different benchmark
arguments:
  --model MODEL             model path
  --metric {emf1,nlg,clas}  evaluate metric
  --valid VALID             evaluate data path

optional arguments:
  -h, --help            show this help message and exit
  --print               print each pair of evaluate data
  --enable_arg_panel    enable panel to input argument

Contributing

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 www.flaticon.com
Icons modify from Nikita Golubev from www.flaticon.com

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-0.3.40.tar.gz (31.9 kB view details)

Uploaded Source

Built Distribution

tfkit-0.3.40-py3-none-any.whl (50.6 kB view details)

Uploaded Python 3

File details

Details for the file tfkit-0.3.40.tar.gz.

File metadata

  • Download URL: tfkit-0.3.40.tar.gz
  • Upload date:
  • Size: 31.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/2.0.0 pkginfo/1.5.0.1 requests/2.23.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.46.1 CPython/3.7.4

File hashes

Hashes for tfkit-0.3.40.tar.gz
Algorithm Hash digest
SHA256 97a76c3ded0726f2c4a33a7e004fbe402cfc744a917f96882950a5f5ff8249d4
MD5 1602799ef1ce83b18d871e33fddfc3a8
BLAKE2b-256 317f108f6cd0fe9ce93fad98a125522773284dccca62523c016b4e8ae54e2c81

See more details on using hashes here.

File details

Details for the file tfkit-0.3.40-py3-none-any.whl.

File metadata

  • Download URL: tfkit-0.3.40-py3-none-any.whl
  • Upload date:
  • Size: 50.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/2.0.0 pkginfo/1.5.0.1 requests/2.23.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.46.1 CPython/3.7.4

File hashes

Hashes for tfkit-0.3.40-py3-none-any.whl
Algorithm Hash digest
SHA256 8b4ec740eee779fdcd70fb4a123006d607caac23b80afbf95973f720572b06a1
MD5 9014f904136639fb48db1ccb81483d4c
BLAKE2b-256 24f112da06cd0990bb84cf50e600ef65f65349f6d4f406553366f0e7ee4bd3a1

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page