Individual skill
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.
tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training/SKILL.md
Source commit f860ecf02ef53412a030f8661c83d644b739ff01
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 3, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,906
- Repository last updated
- Nov 4, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- benchmark Repository topic
- skillsbench Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 3,527 bytesSKILL.mdcore · 3,527 bytesSKILL.mdcore · 3,527 bytesSKILL.mdcore · 3,527 bytesreferences/fineweb-data.mddoc · 3,609 bytesreferences/gpt-architecture.mddoc · 4,630 bytesreferences/hyperparameters.mddoc · 2,760 bytesreferences/optimizers.mddoc · 3,077 bytesreferences/tokenized-data.mddoc · 4,129 bytesreferences/training-loop.mddoc · 3,648 bytes
Read excerpt
# 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