---
title: "generative-ai-for-beginners vs LLMs-from-scratch"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/microsoft-generative-ai-for-beginners-vs-rasbt-llms-from-scratch"
tools: ["microsoft-generative-ai-for-beginners", "rasbt-llms-from-scratch"]
---

# generative-ai-for-beginners vs LLMs-from-scratch

*GraphCanon updated Jul 11, 2026*

## Verdict

Pick generative-ai-for-beginners when license: generative-ai-for-beginners is MIT, LLMs-from-scratch is Other; pick LLMs-from-scratch when license: LLMs-from-scratch is Other, generative-ai-for-beginners is MIT.

[generative-ai-for-beginners](https://github.com/microsoft/generative-ai-for-beginners) reports 113k GitHub stars, 61k forks, and 7 open issues, last pushed Jul 9, 2026. [LLMs-from-scratch](https://amzn.to/4fqvn0D) has 99k stars, 15k forks, and 4 open issues, last pushed Jun 2, 2026. Figures are from public GitHub metadata via [generative-ai-for-beginners's repository](https://github.com/microsoft/generative-ai-for-beginners) and [LLMs-from-scratch's repository](https://github.com/rasbt/LLMs-from-scratch).

| | [generative-ai-for-beginners](/tools/microsoft-generative-ai-for-beginners.md) | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) |
| --- | --- | --- |
| Tagline | 21 Lessons, Get Started Building with Generative AI | Implement a ChatGPT-like LLM in PyTorch from scratch, step by step |
| Stars | 112,866 | 98,899 |
| Forks | 60,628 | 15,183 |
| Open issues | 7 | 4 |
| Language | Jupyter Notebook | Jupyter Notebook |
| Adopt for | - | LLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions. |
| Persona | - | - |
| Runtime | - | - |
| License | MIT | Other |
| Categories | LLM Frameworks, Model Training | LLM Frameworks, Model Training |

## Trust and health

_Sourced signals - not a safety guarantee. No winner column._

| | [generative-ai-for-beginners](/tools/microsoft-generative-ai-for-beginners.md) | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) |
| --- | --- | --- |
| Maintenance | Very active (96%) | Steady (60%) |
| Days since push | 2d | 38d |
| Open issues (now) | 7 | 4 |
| Owner type | Organization | User |
| Full report | [trust report](/tools/microsoft-generative-ai-for-beginners/trust.md) | [trust report](/tools/rasbt-llms-from-scratch/trust.md) |

## Decision facts: LLMs-from-scratch

- **Adopt for:** LLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions.

## Choose when

### Choose generative-ai-for-beginners if…

- License: generative-ai-for-beginners is MIT, LLMs-from-scratch is Other.
- Tags unique to generative-ai-for-beginners: azure, chatgpt, dall-e, generativeai.
- More GitHub stars (113k vs 99k) - visibility, not fit.

### Choose LLMs-from-scratch if…

- License: LLMs-from-scratch is Other, generative-ai-for-beginners is MIT.
- Tags unique to LLMs-from-scratch: artificial-intelligence, attention mechanism, deep-learning, finetuning.
- - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework.

## When NOT to use generative-ai-for-beginners

- LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves.
- Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge.

## When NOT to use LLMs-from-scratch

- - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work.
- - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers丰
- a deeper learning experience.

## Common questions

### What is the difference between generative-ai-for-beginners and LLMs-from-scratch?

generative-ai-for-beginners: 21 Lessons, Get Started Building with Generative AI. LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. See the comparison table for live GitHub stats and shared categories.

### When should I choose generative-ai-for-beginners over LLMs-from-scratch?

Choose generative-ai-for-beginners over LLMs-from-scratch when License: generative-ai-for-beginners is MIT, LLMs-from-scratch is Other; Tags unique to generative-ai-for-beginners: azure, chatgpt, dall-e, generativeai; More GitHub stars (113k vs 99k) - visibility, not fit.

### When should I choose LLMs-from-scratch over generative-ai-for-beginners?

Choose LLMs-from-scratch over generative-ai-for-beginners when License: LLMs-from-scratch is Other, generative-ai-for-beginners is MIT; Tags unique to LLMs-from-scratch: artificial-intelligence, attention mechanism, deep-learning, finetuning; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework.

### When should I avoid generative-ai-for-beginners?

LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge.

### When should I avoid LLMs-from-scratch?

- If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work. - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers丰 a deeper learning experience.

### Is generative-ai-for-beginners or LLMs-from-scratch more popular on GitHub?

generative-ai-for-beginners has more GitHub stars (112,866 vs 98,899). Stars measure visibility, not whether either tool fits your constraints.

### Are generative-ai-for-beginners and LLMs-from-scratch open source?

Yes - both are open-source projects on GitHub (generative-ai-for-beginners: MIT, LLMs-from-scratch: Other).

### Where can I find alternatives to generative-ai-for-beginners or LLMs-from-scratch?

GraphCanon lists graph-backed alternatives at [generative-ai-for-beginners alternatives](/tools/microsoft-generative-ai-for-beginners/alternatives) and [LLMs-from-scratch alternatives](/tools/rasbt-llms-from-scratch/alternatives) ([generative-ai-for-beginners markdown twin](/tools/microsoft-generative-ai-for-beginners/alternatives.md), [LLMs-from-scratch markdown twin](/tools/rasbt-llms-from-scratch/alternatives.md)), ranked by typed relationship edges rather than popularity votes.

### Is there a machine-readable version of this comparison?

Yes. The markdown twin at [this comparison](/compare/microsoft-generative-ai-for-beginners-vs-rasbt-llms-from-scratch.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.

### Which is better maintained, generative-ai-for-beginners or LLMs-from-scratch?

generative-ai-for-beginners: Very active. LLMs-from-scratch: Steady. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.

### Where are the full trust reports for generative-ai-for-beginners and LLMs-from-scratch?

GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [generative-ai-for-beginners trust report](/tools/microsoft-generative-ai-for-beginners/trust); [LLMs-from-scratch trust report](/tools/rasbt-llms-from-scratch/trust).

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/graph?tool=microsoft-generative-ai-for-beginners`](/api/graphcanon/graph?tool=microsoft-generative-ai-for-beginners)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_
