One-page printable decision sheet: the prompt-vs-retrieve-vs-fine-tune test, the LoRA/QLoRA GPU-memory cheat-sheet, dataset-size and labelling-budget rules of thumb, and the catastrophic-forgetting check.
Download free PDF
The book · Volume 6 of 7
AI for Video: A Complete Guide to Intelligence in Video Products: From Models and Inference to Computer Vision, Speech, Search, and Generative Video
This VLM fine-tuning checklist runs the prompt, retrieve or fine-tune test, gives LoRA and QLoRA GPU-memory numbers, dataset and labeling budgets and a catastrophic-forgetting check. Volume 6 covers this in depth: the lifecycle of an AI feature, model artifacts and the ML basics for decisions, deployment topologies and computer vision tasks. Written by Nikolay Sapunov, CEO at Fora Soft.
Deciding whether to fine-tune a VLM or keep prompting it?
Share your task and sample data: we will run the prompt-versus-fine-tune test, size the dataset and GPUs and estimate the training cost. 250+ video products shipped since 2005.
You get a realistic estimate, technical recommendations and next steps. Free, no obligations.
