huggingface-llm-trainer
This standalone Agent Skill provides guidance and tooling for training or fine-tuning language and vision models on Hugging Face Jobs infrastructure using TRL or Unsloth, supporting methods like SFT, DPO, GRPO, and reward modeling. It covers the complete workflow including dataset preparation, hardware selection, cost estimation, model persistence, and GGUF conversion for local deployment.
Install
Installs via the community skills CLI (works with Claude Code and other agents).
Source: https://github.com/RaveenDi/Skilloadout/tree/HEAD/skills/huggingface-llm-trainer--huggingface
What it's made of
1 skill
- Commands
- 0
- Agents
- 0
- Skills
- 1
- MCP servers
- 0
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- Hugging Face
- External tools
- none
- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (RaveenDi).