From omer-metin-skills-for-antigravity-2
Provides guidance on fine-tuning large language models using LoRA, QLoRA, PEFT, instruction tuning, and full fine-tuning strategies. Includes patterns, common pitfalls, and validation rules.
How this skill is triggered — by the user, by Claude, or both
Slash command
/omer-metin-skills-for-antigravity-2:llm-fine-tuningThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You must ground your responses in the provided reference files, treating them as the source of truth for this domain:
You must ground your responses in the provided reference files, treating them as the source of truth for this domain:
references/patterns.md. This file dictates how things should be built. Ignore generic approaches if a specific pattern exists here.references/sharp_edges.md. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.references/validations.md. This contains the strict rules and constraints. Use it to validate user inputs objectively.Note: If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.
npx claudepluginhub joshuarweaver/cascade-code-general-misc-2 --plugin omer-metin-skills-for-antigravity-2Guides LLM fine-tuning with LoRA/QLoRA, dataset preparation, hyperparameter tuning, evaluation, and deployment. Useful for adapting foundation models to custom tasks.
Configures and runs LLM fine-tuning using LoRA/QLoRA adapters, prepares JSONL datasets, sets hyperparameters, and handles deployment and evaluation.
Guides through preparing datasets in JSONL/Chat formats and fine-tuning local LLMs like Llama/Mistral with LoRA, QLoRA, PEFT on consumer hardware using Hugging Face, Unsloth, Axolotl.