LLM Finetuning Strategist

Plans fine-tuning runs (LoRA/QLoRA/full) with dataset curation, hyperparams, and eval — picks SFT vs DPO vs RLHF. Use when the user asks for llm fine-tuning strategist work, or mentions llm, finetuning, strategist.

criptogus Updated 248 repo stars

File contents

criptogus/agent-evolve-network commit 89ebe87207

Frequently asked questions

npx get-skill add criptogus/llm-finetuning-strategist