jiant is a work-in-progress software toolkit for natural language processing research, designed to facilitate work on multitask learning and transfer learning for sentence understanding tasks.
jiantis configuration-driven. You can run an enormous variety of experiments by simply writing configuration files. Of course, if you need to add any major new features, you can also easily edit or extend the code.
jiantcontains implementations of strong baselines for the GLUE and SuperGLUE benchmarks, and it's the recommended starting point for work on these benchmarks.
jiantwas developed at the 2018 JSALT Workshop by the General-Purpose Sentence Representation Learning team and is maintained by the NYU Machine Learning for Language Lab, with help from many outside collaborators (especially Google AI Language's Ian Tenney).
jiantis built on PyTorch. It also uses many components from AllenNLP and the HuggingFace PyTorch Transformers package.
jiantor to install a copy yourself, have a look at our GitHub repository.