← Browse
llm-finetuning
wshobson ★ 775
This plugin provides a complete LLM fine-tuning workflow supporting LoRA/QLoRA supervised fine-tuning, preference optimization methods (DPO/ORPO/KTO), reinforcement learning (GRPO/RLVR), vision model tuning, and quantized export — using Unsloth as the primary backend with TRL fallback. Fine-tuning operations are gated by evaluation results, meaning no evaluation harness prevents the fine-tune from proceeding.
Install
> /plugin marketplace add wshobson/agents/tree/HEAD/plugins/llm-finetuning
> /plugin install llm-finetuning
Source: https://github.com/wshobson/agents/tree/HEAD/plugins/llm-finetuning
What it's made of
2 commands · 3 agents · 10 skills
- Commands
- 2
- Agents
- 3
- Skills
- 10
- MCP servers
- 0
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
- none
- Talks to
- nothing external detected
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 (wshobson).