Skip to content
Agentmart
Submit a tool

ml-training

Machine learning model training with HuggingFace.

Skill by neuron-one

IndexedMIT★ 36
Write a review

Install

Works with Claude Code. Read the repository before you give any tool access to your data.

npx agentmarket install skill/neuron-one-ml-training

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Machine learning model training with HuggingFace. Fine-tuning LLMs, dataset creation, GPU selection, training monitoring. Use for training custom models. Don't use for using pre-trained models via API.

Use cases: backend, ml

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ml-training

Tools it pre-approves 6

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Read,
  • Write,
  • Edit,
  • Bash,
  • Grep,
  • WebFetch

What's inside

Skill name
ml-training
Description
Machine learning model training with HuggingFace. Fine-tuning LLMs, dataset creation, GPU selection, training monitoring. Use for training custom models. Don't use for using pre-trained models via API.
License
MIT
Allowed tools
Read,, Write,, Edit,, Bash,, Grep,, WebFetch
Instructions
27 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves some shell commands

Files (1)

  • SKILL.md

SKILL.md (first lines)

# ML Model Training

## Pipeline
1. Define task and success metrics
2. Collect/prepare training data
3. Choose base model (by size and task fit)
4. Select GPU and estimate cost
5. Configure training (SFT, DPO, or GRPO)
6. Monitor training run
7. Evaluate on test set
8. Deploy model

## Model Selection
- Small tasks (classification): Qwen 0.6B-3B
- Medium tasks (generation): Mistral 7B, Llama 8B
- Complex tasks (reasoning): Qwen 27B, Llama 70B

## Training Methods
- SFT: supervised fine-tuning on examples
- DPO: preference optimization (good vs bad)
- GRPO: group relative policy optimization

## Deployment
- Ollama for local inference
- LitServe for MCP server
- llama.cpp for production

From neuron-one/GODMODE, MIT.

More from neuron-one/GODMODE

Signals

Stars
36
Forks
11
Open issues
0
Last commit (this folder)
Apr 1, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/neuron-one/GODMODE
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from neuron-one

Cite this page

ml-training skill. Agent Mart. https://agentmart.dev/skills/neuron-one-ml-training (last updated 2026-10-24)