Saeed Mohseni seh deh
  • Bio
  • Papers
  • Experience
  • Projects
  • Projects
    • TinyStories LLM, Building a Small Language Model from Scratch
    • Simulation Study of the Metropolis-Hastings Algorithm for Distribution Sampling
    • Gaussian Process Regression for Robotic Arm Modeling
    • Solar Flare Detection via GLR-Based Change-Point Analysis
  • Projects
  • Experience
    • index
  • Blog
    • ๐ŸŽ‰ Easily create your own simple yet highly customizable blog
    • ๐Ÿง  Sharpen your thinking with a second brain
    • ๐Ÿ“ˆ Communicate your results effectively with the best data visualizations
    • ๐Ÿ‘ฉ๐Ÿผโ€๐Ÿซ Teach academic courses
    • โœ… Manage your projects
  • Publications
    • Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance
    • Causal Digital Twins for Physical System Control
    • Induced Covariance for Causal Discovery in Linear Sparse Structures
    • A fast dictionary-learning-based classification scheme using undercomplete dictionaries
  • Teaching
    • Learn JavaScript
    • Learn Python

TinyStories LLM, Building a Small Language Model from Scratch

Oct 1, 2024 ยท 1 min read
Go to Project Site

From tokenizer to transformer โ€” a hands-on exploration of how large language models learn, implemented and trained entirely from scratch on TinyStories using PyTorch.

Last updated on Oct 17, 2025
LLM
Saeed Mohseni seh deh
Authors
Saeed Mohseni seh deh
PhD student

Simulation Study of the Metropolis-Hastings Algorithm for Distribution Sampling May 1, 2024 →

ยฉ 2025 Me. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder โ€” the free, open source website builder that empowers creators.