What is fine-tuning of an LLM?

Question

Accepted Answer

Further training a pretrained model on custom data to adjust its weights — Fine-tuning continues training and updates the model's weights on your examples. Prompting and RAG leave the weights untouched — they only change the input the model sees.

Answer

Writing detailed prompts that steer a pretrained model at request time

Answer

Attaching a document store so the model can look facts up at query time

Answer

Compressing a pretrained model to lower precision for cheaper inference

What is fine-tuning of an LLM?

Why this is the answer

More Customizing LLMs: Fine-tuning, LoRA & RAG flashcards