Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
Train GPT-2 scale models (~124M parameters) efficiently on a single GPU.
Install Nanogpt Training
$ npx skills add benchflow-ai/skillsbench --skill nanogpt-training -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install benchflow-ai/skillsbench nanogpt-training --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .claude/skills && cp -r skills-src/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training .claude/skills/nanogpt-training && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "nanogpt-training" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training into .claude/skills/nanogpt-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nanogpt-training", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-trainingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add benchflow-ai/skillsbench --skill nanogpt-training -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install benchflow-ai/skillsbench nanogpt-training --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .agents/skills && cp -r skills-src/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training .agents/skills/nanogpt-training && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "nanogpt-training" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training into .agents/skills/nanogpt-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nanogpt-training", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add benchflow-ai/skillsbench --skill nanogpt-training -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install benchflow-ai/skillsbench nanogpt-training --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training .cursor/skills/nanogpt-training && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "nanogpt-training" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training into .cursor/skills/nanogpt-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nanogpt-training", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/benchflow-ai/skillsbench.git --path tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add benchflow-ai/skillsbench --skill nanogpt-training -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install benchflow-ai/skillsbench nanogpt-training --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training .gemini/skills/nanogpt-training && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "nanogpt-training" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training into .gemini/skills/nanogpt-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nanogpt-training", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install benchflow-ai/skillsbench nanogpt-trainingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add benchflow-ai/skillsbench --skill nanogpt-training -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .github/skills && cp -r skills-src/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training .github/skills/nanogpt-training && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "nanogpt-training" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training into .github/skills/nanogpt-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nanogpt-training", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add benchflow-ai/skillsbench --skill nanogpt-training -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install benchflow-ai/skillsbench nanogpt-training --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training .opencode/skills/nanogpt-training && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "nanogpt-training" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training into .opencode/skills/nanogpt-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nanogpt-training", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
nanogpt-training- GitHub stars
- 1.8k
- Token cost
- ~882 tokens
- SKILL.md length
- 194 words
- Files
- 7 (incl. references)
- Skills in repo
- 189
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Train GPT-2 scale models (~124M parameters) efficiently on a single GPU.
- Tasks that involve Deep learning
- SKILL.md covers Overview, Quick Reference, Installation and Minimal Example, plus 4 more sections
- Calls pip
What it does
Nanogpt Training is an agent skill from benchflow-ai/skillsbench. 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.
Its SKILL.md is about 880 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/fineweb-data.md`, `references/gpt-architecture.md` and `references/hyperparameters.md`).
It sits in AI & LLM Engineering, covering Deep learning. It works with Hugging Face. The repository describes itself as: SkillsBench evaluates how well skills work and how effective agents are at using them. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Deep learning
Example prompts
- “/nanogpt-training”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 9a1f4dd. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.comhuggingface.co
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Nanogpt Training loads about 882 tokens when it runs, and up to ~6.3k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 194 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from benchflow-ai/skillsbench at commit 9a1f4dd, republished under its Apache-2.0 licence (© benchflow-ai). 194 words, ~882 tokens.
Download SKILL.mdSave it as
.claude/skills/nanogpt-training/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- nanogpt-training
- description
- 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.
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
pip install torch einops numpy huggingface_hubMinimal Example
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
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 mathWhen 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
© benchflow-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 6 other files (references) in tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training of benchflow-ai/skillsbench.
- SKILL.md
- references/fineweb-data.md
- references/gpt-architecture.md
- references/hyperparameters.md
- references/optimizers.md
- references/tokenized-data.md
- references/training-loop.md
Open the folder on GitHubat commit 9a1f4dd
Compare with similar skills
Nanogpt Training next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Nanogpt Training this skillbenchflow-ai/skillsbench | 1.8k | — | ~882 | Automated safety check: Pass | Apache-2.0 | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Hugging Face AccelerateOrchestra-Research/AI-Research-SKILLs | 13k | 5 repos | ~2.1k | Automated safety check: Pass | MIT | |
| pyvene Causal InterventionsOrchestra-Research/AI-Research-SKILLs | 13k | 2 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Ray Train Distributed TrainingOrchestra-Research/AI-Research-SKILLs | 13k | 2 repos | ~2.7k | Automated safety check: Pass | MIT | |
| torchforge RL TrainingOrchestra-Research/AI-Research-SKILLs | 13k | 2 repos | ~2.5k | Automated safety check: Pass | MIT |
Similar skills
Hugging Face Accelerate
Orchestra-Research/AI-Research-SKILLs
Adds distributed and mixed-precision training to a PyTorch script with a few Accelerate lines, then launches it on one GPU, many GPUs or DeepSpeed and FSDP setups.
pyvene Causal Interventions
Orchestra-Research/AI-Research-SKILLs
Guides causal experiments on PyTorch models with pyvene, such as causal tracing, activation patching and interchange intervention training, to test how a model works.
Ray Train Distributed Training
Orchestra-Research/AI-Research-SKILLs
Scales PyTorch, TensorFlow and Hugging Face training from a single GPU to multi-node clusters with Ray Train, including Ray Tune sweeps and checkpoint recovery.
torchforge RL Training
Orchestra-Research/AI-Research-SKILLs
Guides reinforcement-learning research with torchforge, Meta's PyTorch-native library that keeps RL algorithms apart from infrastructure, including GRPO math-reasoning runs.
Mamba State-Space Models
Orchestra-Research/AI-Research-SKILLs
Guide to using Mamba selective state-space models for linear-time sequence modeling, from the Mamba block and pretrained checkpoints to Mamba-2 and speed comparisons.
More from benchflow-ai/skillsbench
All 189 skills in this repoLean4 Memories
benchflow-ai/skillsbench
This skill should be used when working on Lean 4 formalization projects to maintain persistent memory of successful proof patterns, failed approaches, project conventions, and user preferences…
Senior Data Engineer
benchflow-ai/skillsbench
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure.
Ac Branch Pi Model
benchflow-ai/skillsbench
AC branch pi-model power flow equations (P/Q and |S|) with transformer tap ratio and phase shift, matching acopf-math-model.md and MATPOWER branch fields.
Civ6lib
benchflow-ai/skillsbench
Civilization 6 district mechanics library. An agent skill from benchflow-ai/skillsbench.
D3 Visualization
benchflow-ai/skillsbench
Build deterministic, verifiable data visualizations with D3.js (v6).
Dc Power Flow
benchflow-ai/skillsbench
DC power flow analysis for power systems. An agent skill from benchflow-ai/skillsbench.
Related
Works with
Categories
Questions about Nanogpt Training
What does Nanogpt Training do?
Train GPT-2 scale models (~124M parameters) efficiently on a single GPU. Nanogpt Training is an agent skill from benchflow-ai/skillsbench. Train GPT-2 scale models (~124M parameters) efficiently on a single GPU.
When should I use Nanogpt Training?
Nanogpt Training fits situations like: tasks that involve Deep learning.
How do I install Nanogpt Training in Claude Code?
Run `npx skills add benchflow-ai/skillsbench --skill nanogpt-training -a claude-code`. Or copy the skill folder (tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training in benchflow-ai/skillsbench) into .claude/skills/nanogpt-training in your project. Claude Code loads it when a task matches its description.
How do I install Nanogpt Training in Codex?
Run `npx skills add benchflow-ai/skillsbench --skill nanogpt-training -a codex`. Or copy the skill folder (tasks-extra/mhc-layer-impl/environment/skills/nanogpt-training in benchflow-ai/skillsbench) into .agents/skills/nanogpt-training in your project. Codex loads it when a task matches its description.
Can I use Nanogpt Training in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add benchflow-ai/skillsbench --skill nanogpt-training -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nanogpt-training, .gemini/skills/nanogpt-training, .github/skills/nanogpt-training and .opencode/skills/nanogpt-training in your project.
What does Nanogpt Training need to run?
Going by SKILL.md and its folder, Nanogpt Training needs the command-line tools its instructions call (pip). Our summary lists: Python 3.
Does Nanogpt Training access the network?
SKILL.md names 2 domains. As links in the text: github.com and huggingface.co. This is read from the text; nothing was executed.
Is Nanogpt Training safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Nanogpt Training use?
Nanogpt Training is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Nanogpt Training use?
About 882 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.5k tokens, read only when the agent opens those files.
What are the alternatives to Nanogpt Training?
Skills that share tags, products or a category with Nanogpt Training: Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), Hugging Face Accelerate (Orchestra-Research/AI-Research-SKILLs, 13k stars), pyvene Causal Interventions (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Ray Train Distributed Training (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Nanogpt Training?
benchflow-ai (a GitHub organization) maintains it in benchflow-ai/skillsbench, which has 1,834 GitHub stars. The repository holds 189 skills in this directory. The repository was last updated on July 23, 2026.
Source: benchflow-ai/skillsbench on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.