Learning path
Fine-tuning and Hugging Face
Open models from the Hub, when to fine-tune, and LoRA and QLoRA on one GPU, with animated films and runnable Python. Part of the Gen AI Developer premium track.
-
1
Using Open Models from the Hugging Face Hub
Find, download and run open models from the Hugging Face Hub: model cards, licences, pipelines for common tasks, running small LLMs locally, and choosing a model by size…
-
2
When to Fine-Tune (and When Not To)
Prompting, RAG or fine-tuning? A decision guide with costs, what fine-tuning is good at (style, format, narrow skills, smaller models), how to build a training dataset, and how…
-
3
Fine-Tuning a Small Model with LoRA and QLoRA
Fine-tune an open LLM on one GPU: why full fine-tuning is expensive, how LoRA adapters train a tiny fraction of the weights, QLoRA with 4-bit models, the training…