randomfun

Source

Classification

Summary

Random fun Repo for random scripts and notebooks. License BSD.

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/randomfun
  • Default branch: master
  • HEAD: ae0363ada947b56e5484e2e4e755d2ec468c9687
  • Stars at crawl: 1165
  • Forks at crawl: 141
  • File count: 20
  • README path: README.md
  • License path: “
  • Created: 2015-08-04T18:05:15Z
  • Updated: 2026-04-29T19:28:33Z
  • Pushed: 2023-04-18T17:49:08Z

Top-Level Structure

  • [root]: 14
  • irust: 3
  • lectures: 3

File Extension Profile

  • .ipynb: 14
  • .md: 2
  • .jpeg: 1
  • .jpg: 1
  • .rs: 1
  • .toml: 1

Tags / Release-Like Markers

  • No git tags found in the shallow local clone.

Sample File Tree

  • es.ipynb
  • floats.ipynb
  • irust/hello-rust/Cargo.toml
  • irust/hello-rust/src/main.rs
  • irust/readme.md
  • knn_vs_svm.ipynb
  • lectures/makemore/makemore_part1_bigrams.ipynb
  • lectures/micrograd/micrograd_lecture_first_half_roughly.ipynb
  • lectures/micrograd/micrograd_lecture_second_half_roughly.ipynb
  • MicroGrad.ipynb
  • min-char-rnn-nb.ipynb
  • min-char-rnn-nb2.ipynb
  • min-char-rnn-nb3.ipynb
  • MixtureDensityNets.ipynb
  • nand_to_uint.ipynb
  • puppy.jpg
  • README.md
  • rnnlm.jpeg
  • sexual_reproduction.ipynb
  • transformer_unify.ipynb

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.