Home/Compare/CodeT vs LLMs-from-scratch

Comparison

CodeT vs LLMs-from-scratch

Verdict

Pick CodeT when codeT is primarily Python; LLMs-from-scratch is Jupyter Notebook; pick LLMs-from-scratch when lLMs-from-scratch is primarily Jupyter Notebook; CodeT is Python.

Markdown twin · CodeT alternatives · LLMs-from-scratch alternatives

GraphCanon updated today

CodeT logo

CodeT

microsoft/CodeT

677pushed Nov 1, 2024
vs
LLMs-from-scratch logo

LLMs-from-scratch

rasbt/LLMs-from-scratch

99kpushed Jun 2, 2026

Trust & integrity

SignalCodeTLLMs-from-scratch
Maintenance
Dormant (617d since push)
As of today · github_public_v1
Steady (38d since push)
As of today · github_public_v1
Provenance
Not a fork · Organization account
As of today · github_public_v1
Not a fork · Personal account
As of today · github_public_v1
Security (OSV)
No lockfile
As of today · none
No lockfile
As of today · none

Tagline

CodeT
CodeT
LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Stars

CodeT
677
LLMs-from-scratch
99k

Forks

CodeT
86
LLMs-from-scratch
15k

Open issues

CodeT
10
LLMs-from-scratch
4

Language

CodeT
Python
LLMs-from-scratch
Jupyter Notebook

Adopt for

CodeT
-
LLMs-from-scratch
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

CodeT
-
LLMs-from-scratch
-

Runtime

CodeT
-
LLMs-from-scratch
-

License

CodeT
MIT
LLMs-from-scratch
Other

Last pushed

CodeT
Nov 1, 2024
LLMs-from-scratch
Jun 2, 2026

Categories

CodeT
LLM Frameworks, Data & Retrieval, Model Training
LLMs-from-scratch
Model Training, LLM Frameworks

Trust and health

Maintenance

CodeT
Dormant (18%)
LLMs-from-scratch
Steady (60%)

Days since push

CodeT
617d
LLMs-from-scratch
38d

Open issues (now)

CodeT
10
LLMs-from-scratch
4

Owner type

CodeT
Organization
LLMs-from-scratch
User

Full report

LLMs-from-scratch
Trust report

Choose CodeT if…

  • CodeT is primarily Python; LLMs-from-scratch is Jupyter Notebook.
  • License: CodeT is MIT, LLMs-from-scratch is Other.
  • Tags unique to CodeT: python.
  • Also covers Data & Retrieval.

When NOT to use CodeT

  • Last GitHub push was 617 days ago (dormant maintenance, Nov 1, 2024). Validate activity before betting a new project on CodeT.
  • LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves.
  • Data & Retrieval: Skip a heavy ingestion framework when your corpus is small and static; a script plus the embedding API is enough.
  • Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge.

Choose LLMs-from-scratch if…

  • LLMs-from-scratch is primarily Jupyter Notebook; CodeT is Python.
  • License: LLMs-from-scratch is Other, CodeT is MIT.
  • Tags unique to LLMs-from-scratch: deep-learning, ai, artificial-intelligence, attention-mechanism.
  • - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework.

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.

Explore

Sources

Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.

GitHub stars on cards: CodeT 677 · LLMs-from-scratch 99k (synced Jul 11, 2026).

Common questions

What is the difference between CodeT and LLMs-from-scratch?
CodeT: CodeT. 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 CodeT over LLMs-from-scratch?
Choose CodeT over LLMs-from-scratch when CodeT is primarily Python; LLMs-from-scratch is Jupyter Notebook; License: CodeT is MIT, LLMs-from-scratch is Other; Tags unique to CodeT: python; Also covers Data & Retrieval.
When should I choose LLMs-from-scratch over CodeT?
Choose LLMs-from-scratch over CodeT when LLMs-from-scratch is primarily Jupyter Notebook; CodeT is Python; License: LLMs-from-scratch is Other, CodeT is MIT; Tags unique to LLMs-from-scratch: deep-learning, ai, artificial-intelligence, attention-mechanism; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework.
When should I avoid CodeT?
Last GitHub push was 617 days ago (dormant maintenance, Nov 1, 2024). Validate activity before betting a new project on CodeT. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Data & Retrieval: Skip a heavy ingestion framework when your corpus is small and static; a script plus the embedding API is enough. 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 CodeT or LLMs-from-scratch more popular on GitHub?
LLMs-from-scratch has more GitHub stars (98,899 vs 677). Stars measure visibility, not whether either tool fits your constraints.
Are CodeT and LLMs-from-scratch open source?
Yes - both are open-source projects on GitHub (CodeT: MIT, LLMs-from-scratch: Other).
Where can I find alternatives to CodeT or LLMs-from-scratch?
GraphCanon lists graph-backed alternatives at CodeT alternatives and LLMs-from-scratch alternatives (CodeT markdown twin, LLMs-from-scratch markdown twin), 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 mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
Which is better maintained, CodeT or LLMs-from-scratch?
CodeT: Dormant. 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 CodeT and LLMs-from-scratch?
GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: CodeT trust report; LLMs-from-scratch trust report.