llm-finetuning — Claude Code plugin: what it does, how to install
Guides the end-to-end open-weights fine-tuning lifecycle with mandatory eval gating. Useful for LoRA, DPO, GRPO setups and quantized exports.
/plugin marketplace add wshobson/agents
/plugin install llm-finetuning@claude-code-workflowsWhat llm-finetuning does
The plugin structures the entire lifecycle for fine-tuning open-weights models. It covers LoRA and QLoRA SFT, preference optimization methods like DPO, ORPO, or KTO, reinforcement learning with GRPO/RLVR, and vision SFT.
The workflow enforces an eval-first approach. It requires creating the evaluation harness before selecting a method, preparing datasets, or filtering checkpoints. Unsloth serves as the primary training tool, falling back to TRL when needed.
Completed runs export to quantized GGUF or FP8 formats. Without an evaluation harness ready, fine-tuning will not proceed.
What it helps with
- Build an evaluation harness before starting fine-tuning
- Configure LoRA or QLoRA SFT using Unsloth
- Apply preference optimization using DPO, ORPO, or KTO
- Train reasoning models with GRPO/RLVR or vision SFT
- Export gated checkpoints to GGUF or FP8
Example prompts for the agent
- Build an evaluation harness and prepare a QLoRA fine-tuning run with Unsloth
- Set up a preference tuning pipeline using DPO on the curated dataset
- Evaluate the latest checkpoints and export the final model to GGUF
How to install llm-finetuning
Plugin marketplace
/plugin marketplace add wshobson/agents/plugin install llm-finetuning@claude-code-workflowsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about llm-finetuning
How to install llm-finetuning in Claude Code?
Add the repository first by running /plugin marketplace add wshobson/agents. Then install the plugin with /plugin install llm-finetuning@claude-code-workflows.
What does llm-finetuning do?
It coordinates the fine-tuning process for open-weights models, covering evaluation setup, training via Unsloth or TRL, checkpoint gating, and quantized export.
Which frameworks does the plugin prioritize for training?
It relies on Unsloth as the primary engine and uses TRL as a fallback.
Source text
llm-finetuning · MIT
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
© Seth Hobson · MIT · wshobson/agents
