An easy to use Natural Language Processing library and framework for predicting, training, fine-tuning, and serving up state-of-the-art NLP models.
Bug Squashed
A new Data API that integrates with HuggingFace's Dataset class
A new Tuner API for training and fine-tuning Transformer models
Full integration of the latest fastai library for full access to state-of-the-art practices when training and fine-tuning a model. As improvements are made to the library AdaptNLP will update to accomodate them
A new Result API that most inference modules return. This is a filterable result ensuring that you only get the most relevent information when returning a prediction from the Easy*
modules
train
and eval
capabilities in the Easy*
modules no longer exist, and all training related functionalities have migrated to the Tuner APILanguageModelFineTuner
no longer exists, and the same tuning functionality is in LanguageModelTuner
Complete conversion to the nbdev library format and actions
Complete revamp of the documentation
Inference API entirely relies on fastai_minima and is now built on fastai's Callback System
Integration with fastcore to simplify logic
HuggingFace and Flair ModelHubs, an easier API to interact, search, and download HF and Flair models. Uses huggingface_hub as a backend. Has logged every single Flair model, including those not in the HuggingFace API
Updated to nlp 0.4 -> datasets 1.0+ and multi-label training for sequence classification fixes.
EasySequenceClassifier.train()
Updatesdatasets.Dataset
nowUpdated to transformers 3+, nlp 0.4+, flair 0.6+, pandas 1+
New Features!
EasySequenceClassifier.train()
and EasySequenceClassifier.evaluate()
nlp.Dataset
and transformers.Trainer
for a streamlined training workflowSequenceClassifierTrainer
is still available, but will be transitioned into the EasySequenceClassifier
and deprecatedLMFineTuner
transformers.Trainer
for a streamlined training workflowLMFineTuner
is still available as LMFineTunerManual
, but will be deprecated in later releasesEasyTextGenerator
Split dev requirements #29 #66 Pinned torch #70
Updated to Transformers 2.8.0 which now includes the ELECTRA language model
EasySummarizer
and EasyTranslator
Bug Fix #63model_name_or_path
param in some easy modules