Sebastian Raschka
A prominent educator and technical author in the deep learning field, known for his book and course series including "Build a Large Language Model From Scratch." He specializes in explaining deep learning and large language model technologies from first principles, making foundational concepts accessible through structured educational content.
Timeline (last 90 days)
The course received 705 upvotes, and the podcast host commented that its core value lies in holding nothing back, showing the complete model-building process rather than just teaching API calls.
Sebastian Raschka released a video course on building a reasoning model from scratch.
Sebastian Raschka released an 8-video, 11-hour "building a reasoning model from scratch" course that manually implements evaluation, inference-time scaling, reinforcement learning with verifiable rewards, and distillation on a small pretrained model using Python and PyTorch.
Sebastian Raschka released an 8-episode video course on YouTube, totaling about 11 hours and entirely free.
"Build a Large Language Model from Scratch" has considerable reputation in the field of teaching how to build LLMs from scratch.
Sebastian Raschka released a set of video courses over 11 hours long demonstrating how to train a model small enough to run on a laptop into a reasoning model.
Sebastian Raschka released a video course on building a reasoning model from scratch, containing more than 11 hours of Python and PyTorch coding.
Sebastian Raschka's "Build a LLM from Scratch" series helped many developers truly understand for the first time how each layer inside a language model works.
Most of Sebastian's course code runs on a Mac mini; the goal of the course is to demonstrate the principles of reasoning techniques using small models, rather than to replicate ultra-large models such as DeepSeek V3/V4.
Sebastian Raschka has launched a course series titled "Build A Reasoning Model From Scratch," and the companion book of the same name is now available.
2 more timeline events
All Facts (12)
The course received 705 upvotes, and the podcast host commented that its core value lies in holding nothing back, showing the complete model-building process rather than just teaching API calls.
50%Unverified"Build a Large Language Model from Scratch" has considerable reputation in the field of teaching how to build LLMs from scratch.
50%UnverifiedSebastian Raschka's "Build a LLM from Scratch" series helped many developers truly understand for the first time how each layer inside a language model works.
50%UnverifiedMost of Sebastian's course code runs on a Mac mini; the goal of the course is to demonstrate the principles of reasoning techniques using small models, rather than to replicate ultra-large models such as DeepSeek V3/V4.
50%Unverified"Build a Large Language Model (From Scratch)" by Sebastian Raschka guides readers step by step through implementing an LLM.
50%UnverifiedSebastian Raschka is a machine learning researcher at the University of Wisconsin and the author of 'Build a Large Language Model (From Scratch)'.
50%UnverifiedSebastian Raschka released a video course on building a reasoning model from scratch.
50%UnverifiedSebastian Raschka released an 8-video, 11-hour "building a reasoning model from scratch" course that manually implements evaluation, inference-time scaling, reinforcement learning with verifiable rewards, and distillation on a small pretrained model using Python and PyTorch.
50%UnverifiedSebastian Raschka released an 8-episode video course on YouTube, totaling about 11 hours and entirely free.
50%UnverifiedSebastian Raschka released a set of video courses over 11 hours long demonstrating how to train a model small enough to run on a laptop into a reasoning model.
50%UnverifiedSebastian Raschka released a video course on building a reasoning model from scratch, containing more than 11 hours of Python and PyTorch coding.
50%UnverifiedSebastian Raschka has launched a course series titled "Build A Reasoning Model From Scratch," and the companion book of the same name is now available.
50%