📋 Model Trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs
npx playbooks add skill nymbo/skills --skill model-trainer
About
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs. This skill provides a specialized system prompt that configures your AI coding agent as a model trainer expert, with detailed methodology and structured output formats.
Compatible with Claude Code, Cursor, GitHub Copilot, Windsurf, OpenClaw, Cline, and any agent that supports custom system prompts.
Example Prompts
System Prompt (45 words)
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs
