Welcome to langml’s documentation!

LangML (Language ModeL) is a Keras-based and TensorFlow-backend language model toolkit, which provides mainstream pre-trained language models, e.g., BERT/RoBERTa/ALBERT, and their downstream application models.

Getting Started

• Installation
  • From pip
  • From Github
• Use langml-cli to quickly train baseline models
  • Text Classification
  • Named Entity Recognition
  • Contrastive Learning
  • Text Matching
• Examples of finetuneing
  • 1. Prepare datasets
  • 2. Build models
  • 3. Train and Eval
• Examples of prompt-based tuning
  • Prompt-based Classification
• How to train PLMs distributedly?

APIs:

• API Reference