ng-video-lecture

Source

• Source kind: github-repository
• URL: https://github.com/karpathy/ng-video-lecture
• Discovery source: https://github.com/karpathy/ng-video-lecture
• License: NOASSERTION
• Distribution policy: public-summary-local-archive-only
• Public mirror status: summary-only
• Content hash: 457992e395e56530c6528b08aef32171172e139883b7b76ccec74678d5431570
• First seen: 2026-05-15
• Last changed: 2026-05-15

Classification

• Primary category: LLM training and inference systems
• Corpus source note: 2026-05-15-karpathy-public-corpus
• Project taxonomy: karpathy-project-taxonomy
• Idea map: karpathy-idea-map
• Topic hub: karpathy-public-work

Summary

nanogpt-lecture Code created in the $1videolectureseries,specificallyonthefirstlectureonnanoGPT.PublishinghereasaGithubreposopeoplecaneasilyhackit,walkthroughthegitloghistoryofit,etc.NOTE:sadlyIdidnotgotoomuchintomodelinitializationinthevideolecture,butitisquiteimportantforgoodperformance.Thecurrentcodewilltrainandworkfine,butitsconvergenceisslowerbecauseitstartsoffinanotgreatspotintheweightspace.Pleasesee$1 for init all weights comment, and especially how it calls the init weights function. Even more sadly, the code in this repo i…

What This Teaches

• How modern LLM training or inference can be reduced to compact, inspectable systems.
• Useful as a reference for building mental models of GPT-style models without hiding behind framework scale.

Why It Matters

This is high-priority for Vipin because it connects directly to LLM systems, evaluation, and research implementation judgment.

Repository Snapshot

• Full name: karpathy/ng-video-lecture
• Default branch: master
• HEAD: 52201428ed7b46804849dea0b3ccf0de9df1a5c3
• Stars at crawl: 4714
• Forks at crawl: 1291
• File count: 5
• README path: README.md
• License path: “
• Created: 2023-01-17T05:27:03Z
• Updated: 2026-05-15T16:55:32Z
• Pushed: 2024-01-31T13:43:36Z

Top-Level Structure

• [root]: 5

File Extension Profile

• .py: 2
• .txt: 2
• .md: 1

Tags / Release-Like Markers

• No git tags found in the shallow local clone.

Sample File Tree

• bigram.py
• gpt.py
• input.txt
• more.txt
• README.md

Public Handling Notes

• EXTRACTED: This page records public metadata and a source-grounded summary.
• INFERRED: Full local preservation, when available, is for private/local use unless a license or explicit source policy makes public redistribution safe.
• Do not treat this page as permission to republish unlicensed source text or code wholesale.