fine-tuning-expert

Expert guidance for fine-tuning LLMs with parameter-efficient methods and production optimization. Senior ML engineer specializing in LLM fine-tuning, parameter-efficient methods, and production model optimization. Load detailed guidance based on context: QLoRA variant — add these lines before loading the model to enable 4-bit quantization: Merge adapter into base model for deployment: When implementing fine-tuning, always provide: Documentation - Covers LoRA, QLoRA, and full fine-tuning workflows with Hugging Face PEFT, including dataset validation, hyperparameter configuration, and adapter merging for deployment - Provides a complete minimal working example with LoRA setup, training loop, and quantization variants for memory-constrained environments - Includes five-stage workflow: dataset preparation, method selection, training with checkpoints, evaluation against base model, and production deployment with quantization - Enforces best practices through explicit constraints: mandatory data validation, parameter-efficient methods for large models, loss curve monitoring, and held-out set evaluation before serving - Dataset preparation — Validate and format data; run quality checks before training starts - Checkpoint: python validate_dataset.py --input data.jsonl — fix all errors before proceeding - Method selection — Choose PEFT technique based on GPU memory and task...