172: Transformers and Large Language Models
March 11, 2024, 3 p.m. (8 months, 1 week ago)
0 Comments
172: Transformers and Large Language Models
Intro topic: Is WFH actually WFC?
News/Links:
- Falsehoods Junior Developers Believe about Becoming Senior
- Pure Pursuit
- Tutorial with python code: https://wiki.purduesigbots.com/software/control-algorithms/basic-pure-pursuit
- Video example: https://www.youtube.com/watch?v=qYR7mmcwT2w
- PID without a PHD
- Google releases Gemma
Book of the Show
- Patrick: The Eye of the World by Robert Jordan (Wheel of Time)
- Jason: How to Make a Video Game All By Yourself
Patreon Plug https://www.patreon.com/programmingthrowdown?ty=h
Tool of the Show
- Patrick: Stadia Controller Wifi to Bluetooth Unlock
- Jason: FUSE and SSHFS
Topic: Transformers and Large Language Models
- How neural networks store information
- Latent variables
- Transformers
- Encoders & Decoders
- Attention Layers
- History
- RNN
- Vanishing Gradient Problem
- LSTM
- Short term (gradient explodes), Long term (gradient vanishes)
- RNN
- Differentiable algebra
- Key-Query-Value
- Self Attention
- History
- Self-Supervised Learning & Forward Models
- Human Feedback
- Reinforcement Learning from Human Feedback
- Direct Policy Optimization (Pairwise Ranking)
No comments have been posted yet, be the first one to comment.