nyu-mll/jiant
jiant is an nlp toolkit
Supports multitask and transfer learning across 50+ NLU tasks with configuration-driven workflows, built on PyTorch and integrated with Hugging Face's `transformers` and `datasets` libraries. Enables evaluation on major benchmarks (GLUE, SuperGLUE, XTREME) through a unified interface. Architecture emphasizes modularity and extensibility for research, with both Python API and CLI-based experiment execution.
1,674 stars and 55 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
1,674
Forks
297
Language
Python
License
MIT
Category
Last pushed
Jul 06, 2023
Monthly downloads
55
Commits (30d)
0
Dependencies
20
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/nyu-mll/jiant"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
Tongjilibo/bert4torch
An elegent pytorch implement of transformers
lonePatient/TorchBlocks
A PyTorch-based toolkit for natural language processing
grammarly/gector
Official implementation of the papers "GECToR – Grammatical Error Correction: Tag, Not Rewrite"...
monologg/JointBERT
Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"
backprop-ai/backprop
Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.