Other
FreePyTorch in 1 Hour
No ratings yetBEGINNEREnglish
YouTubeYouTubeMark your own learning status. Opening a course link does not establish enrollment.
Loading saved status…
This tutorial by an AI researcher covers the mechanics behind PyTorch in about an hour: tensors, autograd, the computation graph and gradients, then the training step itself. It is built for people who want to understand what the framework does under the hood, not just call its functions.
The tutorial finishes with a transformer's feed-forward network, tying the basics to a model you will recognize.
The video suits readers with some Python who want the autograd model clear before moving to larger projects. The author's channel focuses on building LLM systems, so the material leans toward modern language models rather than classical machine learning.
*Don't like the Sound Effect?:* https://youtu.be/GaLL7ZeXsWk
*LLM Training Playlist:* https://www.youtube.com/playlist?list=PLRYer4Da-4mIj5AYQczxpFepL_03080UT
*Text:* https://github.com/The-Pocket/PocketFlow-Tutorial-Video-Generator/blob/main/docs/llm/pytorch.md
0:00:00 - Introduction
0:01:55 - torch.tensor
0:07:32 - Autograd & requires_grad
0:09:21 - Computation Graph & .grad_fn
0:12:50 - Element-wise vs. Matrix Multiplication
0:15:25 - Reduction Operations & The dim Argument
0:30:25 - loss.backward()
0:34:12 - Gradient Descent Update Rule
0:40:23 - torch.nn.Module
0:52:19 - torch.optim
0:57:30 - Transformer Feed-Forward Network
*Social media:*
X: https://x.com/ZacharyHuang12
LinkedIn: https://www.linkedin.com/in/zachary-h-23aa37172/
Github: https://github.com/zachary62
Discord: https://discord.com/invite/hUHHE9Sa6T
Medium: https://medium.com/@zh2408
Substack: https://zacharyhuang.substack.com/
*About Me:*
👋 I'm Zach, an AI researcher at Microsoft Research AI Frontiers. I currently work on LLM Agents & Systems. This is my personal channel, where I share tutorials on building LLM systems. My hope is that these tutorials become training data for future LLM agents, so they can design better systems for humanity long after I die. Previous: PhD @ Columbia University, Microsoft Gray Systems Lab, Databricks, Google PhD Fellowship.
Advertisement
No Korshub reviews yet.
