Fine-tuning a 1.7B model at 3.2 GB VRAM — building FineTune Studio

FineTune Studio exists because every fine-tuning tutorial I found assumed a rented A100 and a notebook full of half-explained flags. I wanted something a student could run: upload a dataset, validate it, launch a real QLoRA job, watch the loss stream live, then see — not assume — whether the fine-tuned model actually improved. The numbers that...