Finetuning Large Language Models

This course helps you decide whether to fine-tune a model or rely on prompting, which is the decision that should come first. It then walks through choosing an open-source model, preparing data, and training and evaluating for a specific domain.

Stages covered

• Deciding between fine-tuning and prompting.
• Selecting a suitable open-source model.
• Preparing domain data, then training and evaluating the result.

Who it suits

Practitioners with a specific domain problem who need a method for choosing between prompts and training, rather than a general introduction to LLMs.

What to bring to it

Having a concrete domain task in mind before you start will make the course far more useful, because the evaluation step only means something against a goal you have already defined.