Course Overview
Learn how to apply and fine-tune a Transformer-based Deep Learning model to Natural Language Processing (NLP) tasks.
In this course, you'll:
- Construct a Transformer neural network in PyTorch
- Build a named-entity recognition (NER) application with BERT
- Deploy the NER application with ONNX and TensorRT to a Triton inference server
Upon completion, you’ll be proficient in task-agnostic applications of Transformer-based models.
Prerequisites
- Experience with Python coding and use of library functions and parameters
- Fundamental understanding of a deep learning framework such as TensorFlow, PyTorch, or Keras
- Basic understanding of neural networks
Course Objectives
- How transformers are used as the basic building blocks of modern LLMs for NLP applications
- How self-supervision improves upon the transformer architecture in BERT, Megatron, and other LLM variants for superior NLP results
- How to leverage pretrained, modern LLM models to solve multiple NLP tasks such as text classification, named-entity recognition (NER), and question answering
- Leverage pre-trained, modern NLP models to solve multiple tasks such as text classification, NER, and question answering
- Manage inference challenges and deploy refined models for live applications
Course Content
Introduction
- Meet the instructor.
- Create an account at courses.nvidia.com/join
Introduction to Transformers
- Explore how the transformer architecture works in detail:
- Build the transformer architecture in PyTorch.
- Calculate the self-attention matrix.
- Translate English to German with a pretrained transformer model.
Self-Supervision, BERT, and Beyond
Learn how to apply self-supervised transformer-based models to concrete NLP tasks using NVIDIA NeMo:
- Build a text classification project to classify abstracts.
- Build a NER project to identify disease names in text.
- Improve project accuracy with domain-specific models.
Inference and Deployment for NLP
- Learn how to deploy an NLP project for live inference on NVIDIA Triton:
- Prepare the model for deployment.
- Optimize the model with NVIDIA® TensorRT™.
- Deploy the model and test it.
Final Review
- Review key learnings and answer questions.
- Complete the assessment and earn a certificate.
- Take the workshop survey.
- Learn how to set up your own environment and discuss additional resources and training.
German