Fine Tuning Expert
Skill Verified ActiveUse 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.
To serve as an expert resource for anyone fine-tuning LLMs, offering best practices, code examples, and configuration guidance for various stages of the process.
Features
- Detailed LoRA/QLoRA configuration guidance
- Dataset preparation and validation utilities
- Hyperparameter tuning strategies and examples
- Code examples for training and deployment
- Best practices for PEFT and model optimization
Use Cases
- Configuring LoRA/QLoRA adapters for custom LLM tasks
- Preparing and validating JSONL training datasets
- Setting hyperparameters for fine-tuning runs
- Optimizing fine-tuned models for deployment
- Adapting foundation models with PEFT methods
Non-Goals
- Performing the fine-tuning process itself (provides guidance, not execution)
- Training foundation models from scratch
- Managing cloud infrastructure for training
- Handling non-ML related tasks
Installation
First, add the marketplace
/plugin marketplace add jeffallan/claude-skills/plugin install claude-skills@fullstack-dev-skillsQuality Score
VerifiedSimilar Extensions
Peft Fine Tuning
99Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
PEFT Fine Tuning
96Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
Unsloth
98Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Implementing Llms Litgpt
98Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
Implementing Llms Litgpt
100Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
Unsloth
100Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization