Published on

News You Can Use - Practical Stuff


Sam Witteveen and I started the Machine Learning Singapore Group (or MLSG for short) on MeetUp in February 2017 (it was previously named "TensorFlow and Deep Learning Singapore"), and the fortieth MeetUp was our third 'in-person' event since the COVID era.

For this event we decided to go for a MeetUp about 'practical' and 'hands on' topics - which is why our speaker line-up focussed on PyTorch Lightning, techniques for using an training large models, and the super-new langchain framework. As far as we know, this was Asia's first/largest langchain meetups to-date.

Many thanks to the Google team, who not only allowed us to use Google's Developer Space, and put out the extra chairs required for our larger-than-expected attendence, but were also kind enough to provide Pizza for the attendees!

This month's event was on the topic "LLMs + Frameworks (ToolFormer, Langchain, & Lightning)", and included three talks:

  1. News You Can Use - Martin Andrews :
  • So many papers, so little time! Martin will pick out a selection of interesting new directions being talked about - with an emphasis on those that can be most immediately useful (i.e. not just reserved for large teams at huge scale).
  1. PyTorch Lightning - Vivek Kalyan :
  • By imposing a little bit of structure, PyTorch Lightning can provide a solid foundation around the model-building process. Vivek will explain how this works in practice, and how it can simplify your workflow.
  1. Langchain - Building apps with LLMs - Sam Witteveen
  • Actually building real world apps with Large Language models can be a challenge on many fronts. Recently the open source frameworks Langchain and GPT Index have come along to make this much easier and add a variety of tools as addons for LLM apps.

The slides for my talk, which contain links to all of the reference materials and sources, are here :

Presentation Screenshot

If there are any questions about the presentation please ask below, or contact me using the details given on the slides themselves.

Presentation Content Example