# fine-tuning-expert

> Claude/Codex skill by [@jeffallan](https://omgskills.com/library/jeffallan/index.md) · 12k stars · Updated 2026-10-30

Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom model.

Tags: ai-agents, claude, claude-code, claude-marketplace, claude-skills

## Install

```sh
git clone https://github.com/Jeffallan/claude-skills /tmp/claude-skills && ln -s /tmp/claude-skills/skills/fine-tuning-expert ~/.claude/skills/fine-tuning-expert
```

## From README

Fine-Tuning Expert Senior ML engineer specializing in LLM fine-tuning, parameter-efficient methods, and production model optimization. Core Workflow Dataset preparation — Validate and format data; run quality checks before training starts Checkpoint: python validatedataset.py --input data.jsonl — fix all errors before proceeding Method selection — Choose PEFT technique based on GPU memory and task requirements Use LoRA for most tasks; QLoRA (4-bit) when GPU memory is constrained; full fine-tune only for small models Training — Configure hyperparameters, monitor loss curves, checkpoint regularly Checkpoint: validation loss must decrease; plateau or increase signals overfitting Evaluation — Benchmark against the base model; test on held-out set and edge cases Checkpoint: collect perplexity, task-specific metrics (BLEU/ROUGE), and latency numbers Deployment — Merge adapter weights, quantize, measure inference throughput before serving Reference Guide Load detailed guidance based on...

## Links

- HTML page: https://omgskills.com/library/jeffallan/claude-skills/fine-tuning-expert/
- GitHub: https://github.com/Jeffallan/claude-skills
- Author: [@jeffallan](https://omgskills.com/library/jeffallan/index.md)

## More from this repo

- [api-designer](https://omgskills.com/library/jeffallan/claude-skills/api-designer/index.md) — Used when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture.
   - [@jeffallan](https://omgskills.com/library/jeffallan/index.md) · 12k stars
- [architecture-designer](https://omgskills.com/library/jeffallan/claude-skills/architecture-designer/index.md) — Used when designing new high-level system architecture, reviewing existing designs, or making architectural decisions.
   - [@jeffallan](https://omgskills.com/library/jeffallan/index.md) · 12k stars
- [atlassian-mcp](https://omgskills.com/library/jeffallan/claude-skills/atlassian-mcp/index.md) — Integrates with Atlassian products to manage project tracking and documentation via MCP protocol.
   - [@jeffallan](https://omgskills.com/library/jeffallan/index.md) · 12k stars