# VikParuchuri/zero_to_gpt

Go from no deep learning knowledge to implementing GPT.

Repository: https://github.com/VikParuchuri/zero_to_gpt
Canonical: https://ross.abutalabs.com/products/zero_to_gpt
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: deep-learning, python, pytorch, tutorial
Last push: 2024-05-30T04:02:33+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 97
- inputs: {"age_days": 1370, "days_push": 825, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1309, forks 222 (observed 2026-08-28T04:04:19.385939+00:00)

## What it is
A free course of Jupyter notebooks that takes learners from no deep learning knowledge to implementing a GPT model from scratch in Python and PyTorch. It covers fundamentals like gradient descent, dense and recurrent networks, backpropagation, and advanced topics like transformers, GPU programming, and distributed training.

## Use cases
- learn deep learning from scratch
- implement GPT from scratch
- understand backpropagation and gradient descent
- learn how transformers work
- train a language model in PyTorch
- study neural network fundamentals with hands-on notebooks

## When to choose
- you know Python and want a hands-on path from neural network basics to building GPT
- you prefer learning by implementing models yourself in notebooks
- you want both theory and practical training examples like weather prediction and translation

## When to avoid
- you need a production-ready training framework or library
- you want a no-code or GUI-based learning tool
- you already need advanced MLOps or fine-tuning workflows rather than fundamentals

## Facets
- artifact type: learning-resource
- maturity: active
- function: deep-learning, machine-learning, llm-training
- domain: deep-learning, large-language-models, tutorials, education
- platform: python
- tags: pytorch, jupyter-notebooks, gpt, transformers, course, neural-networks, gradient-descent, backpropagation

## Member repositories
- VikParuchuri/zero_to_gpt (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:19.385939+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:49:58.335019+00:00, confidence not recorded.
  - readme: https://github.com/VikParuchuri/zero_to_gpt (fetched 2026-08-28T04:04:19.385939+00:00, sha 7be3e74b38b4)
- Data as of 2026-08-30T08:39:29.467469+00:00.