workshop overview

workshop overview#

learning objectives#

Welcome to the final workshop in this series, Generating Text! This workshop builds on the previous ones to fine-tune a text generation model with Python. Participants will explore Machine Learning (ML) processes, datasets, and tools, with the goal of customizing a text generator. They will work primarily with the HuggingFace🤗 platform and the transformers library in python. At the end of the workshop, students will take a peak into the process of fine-tuning a model on the Princeton High Performance Computing (HPC) clusters.

This workshop introduces:

  • ML concepts like word vectors and prediction with word2vec

  • the HuggingFace🤗 platform for models and datasets in ML

  • running inference, loading datasets, and fine-tuning ML models with Python

  • the transformers library in Python

  • high performance cluster computing at Princeton

Contents