ai-pretraining SKILL.md skillA
ai-pretraining from vasilyu1983/ai-agents-public is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add vasilyu1983/ai-agents-public/ai-pretraining@v1.5Pins v1.5 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- vasilyu1983/ai-agents-public
- Path
skills/universal/ai-pretraining/SKILL.md- Versions recorded
- 1
- Latest version
- v1.5, committed Oct 5, 2026
- Size
- 19,745 bytes
- Repository stars
- 101
- License
- MIT
Builds a GPT and BPE tokenizer from scratch. Use when implementing autograd, attention, a nanoGPT loop, muP hyperparameter transfer, WSD annealing, loss spikes, or mid-training.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Pretraining From Scratch **Domain**: building a transformer/GPT and a BPE tokenizer from first principles — the from-first-principles training-layer competency. Does NOT cover applications-layer fine-tuning, RLHF, or inference optimization; those belong to sibling skills. Canonical teachers: Karpathy "Neural Networks: Zero to Hero" (micrograd → makemore → "Let's build GPT" → "Let's build the GPT Tokenizer" → "Let's reproduce GPT-2"), Karpathy nanochat (full-stack from-scratch successor to nanoGPT), Raschka "Build a Large Language Model From Scratch", nanoGPT, minbpe, "Attention Is All You Need". GPT-2 is the pedagogical spine here — the right thing to build *first*. The modern from-scratch baseline then swaps four components onto that spine (RoPE, RMSNorm, SwiGLU, GQA) and runs attention through FlashAttention/SDPA; see [Modern Architecture Deltas](references/modern-architecture-deltas.md). ## When to Use This Skill Activate when the user asks about: - Implementing autograd / backprop from scratch (micrograd-style) - Building makemore (bigram, MLP, WaveNet-style character LMs) - Implementing self-attention, multi-head attention, causal masking …
Read the whole file at its exact version.
How to install
mdr add vasilyu1983/ai-agents-public/ai-pretraining@sha256:0c99bc1d589dbb3fThe line at the top of this page pins the label v1.5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_caxrujyvbs6yzzor)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 5, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (19745 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
vasilyu1983/ai-agents-public · 101 stars · license MIT · pushed 2026-10-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_caxrujyvbs6yzzor GET https://markdownregistry.com/api/v1/resolve?ref=vasilyu1983/ai-agents-public/ai-pretraining GET https://markdownregistry.com/api/v1/blob/0c99bc1d589dbb3f34822242d5d9efa52d8cd50f6ff53595b3c9ca26ab38315b
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.