Jiant is a multitask NLP framework for fine-tuning transformer-based models on multiple natural language understanding (NLU) tasks.

Features

  • Supports multitask learning for NLP model fine-tuning
  • Includes logging and evaluation tools for model comparison
  • Open-source with active research-driven development
  • Provides preconfigured task setups for various benchmarks
  • Allows easy customization for new NLP datasets
  • Integrates with Hugging Face Transformers

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow jiant

jiant Web Site

Other Useful Business Software
Train ML Models With SQL You Already Know Icon
Train ML Models With SQL You Already Know

BigQuery automates data prep, analysis, and predictions with built-in AI assistance.

Build and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
Try Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of jiant!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

Python

Related Categories

Python Natural Language Processing (NLP) Tool

Registered

2025-01-22