Fine-Tuning

Libraries and tools for fine-tuning open-weight models — LoRA/QLoRA adapters, quantization, and memory-efficient training that runs on consumer or single-GPU setups. You reach for these to specialise a base model (Llama, Qwen, Mistral) on your own data without full pretraining. Distinct from ML Frameworks (the underlying training engines) and ML Operations (experiment tracking).