Nanogpt Training

OrganizationPopular

benchflow-ai

nanogpt-training

Train GPT-2 scale models (~124M parameters) efficiently on a single GPU. Covers GPT-124M architecture, tokenized dataset loading (e.g., HuggingFace Hub shards), modern optimizers (Muon, AdamW), mixed precision training, and training loop implementation.

Overview

Publisher	benchflow-ai
Repository	`skillsbench`
Skill name	`nanogpt-training`
Stars	1.8K
Forks	367
Bundled files	6
License	Apache-2.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
6 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by benchflow-ai on GitHub. Read the source before you install it.

Installation

Install the Nanogpt Training AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git /tmp/skillsbench
mkdir -p .claude/skills
cp -r /tmp/skillsbench/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training .claude/skills/nanogpt-training

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Nanogpt Training in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Nanogpt Training on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Nanogpt Training is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

NanoGPT Training

Overview

Training GPT-2 scale models (~124M parameters) efficiently on a single GPU. It provides:

GPT-124M Architecture: Standard transformer with RoPE and modern optimizations
Tokenized Datasets: Loading pre-tokenized shards from HuggingFace Hub or local files
Modern Optimizers: Muon optimizer with Newton-Schulz orthogonalization
Mixed Precision: bfloat16 training on A100 for 2x speedup

Training options:

Baseline GPT: Standard residual connections
Experimental residual variants: Optional alternative residual schemes for stability/efficiency

Quick Reference

Topic	Reference
Model Architecture	GPT Architecture
Data Loading	Tokenized Data
Optimizers	Optimizers
Training Loop	Training Loop
Hyperparameters	Hyperparameters

Installation

bash
pip install torch einops numpy huggingface_hub

Minimal Example

python
import modal

app = modal.App("gpt-training")

image = modal.Image.debian_slim(python_version="3.11").pip_install(
    "torch", "einops", "numpy", "huggingface_hub"
)

@app.function(gpu="A100", image=image, timeout=3600)
def train():
    import torch
    from dataclasses import dataclass

    @dataclass
    class GPTConfig:
        block_size: int = 1024
        vocab_size: int = 50257
        n_layer: int = 12
        n_head: int = 12
        n_embd: int = 768
        dropout: float = 0.0
        bias: bool = False

    # Download data, build model, train
    # ... (see references for full implementation)

    return {"final_loss": final_loss}

@app.local_entrypoint()
def main():
    results = train.remote()
    print(results)

Common Imports

python
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.cuda.amp import autocast, GradScaler
from dataclasses import dataclass
from einops import rearrange, repeat, reduce
import numpy as np
import math

When to Use What

Scenario	Approach
Standard GPT training	Use baseline model with standard residuals
Stability experiments	Try alternative residual variants or extra streams
Small experiments	Use T4/A10G GPU
Full training	Use A100 with bfloat16
Custom data	Modify the dataset loader class
Different model size	Adjust GPTConfig parameters

Metrics to Monitor

Metric	Typical Signal	Notes
Validation loss	Steady decrease	Absolute value depends on dataset/tokenizer
Grad norm	Moderate, stable range	Large spikes indicate instability
Training stability	Smooth curves	Frequent spikes suggest LR/batch issues
Throughput	Consistent tokens/sec	Use for comparing configs

External Resources

nanoGPT: https://github.com/karpathy/nanoGPT
build-nanogpt: https://github.com/karpathy/build-nanogpt
modded-nanogpt: https://github.com/KellerJordan/modded-nanogpt
FineWeb-Edu token shards: https://huggingface.co/datasets/karpathy/fineweb-edu-100B-gpt2-token-shards

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Nanogpt Training AI skill do?

Why use Nanogpt Training on TypingMind?

Because you install it once and use it with any model. Nanogpt Training is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Nanogpt Training in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Nanogpt Training?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Nanogpt Training?

As many as you like. As long as a model supports skills, you can use Nanogpt Training with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Nanogpt Training AI skill free?

Yes. It is published on GitHub by benchflow-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Adr Reindex

ruvnet

CommunityPopular

Reconcile the ADR index against a DELETED ADR file or relation line by dropping and rebuilding adr-patterns + adr-edges from scratch (scripts/reindex.mjs). Use when adr-index alone leaves stale rows…

Cost Export

Export cost-tracking telemetry in Prometheus textfile or webhook JSON formats — for external observability (Grafana, Datadog, custom dashboards)

Daa Agent

Create and adapt Dynamic Agentic Architecture agents that learn and evolve

Data Scientist

Processes and analyzes data with resident-kernel engines (DuckDB, Polars) and one-shot tools. Use for CSV/parquet/JSON analysis, group-by/join/aggregation, time series, distributions, cleaning, or…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

NanoGPT Training

Overview

Quick Reference

Installation

Minimal Example

Common Imports

When to Use What

Metrics to Monitor

External Resources

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now