Back to Artificial Intelligence & LLMs

Fine-Tuning, Instruction Tuning & Prompt Engineering

Adapting pre-trained LLMs for specific downstream tasks.

1 week

Topics in this Chapter

1

Supervised Fine-Tuning (SFT)

Adapting a pre-trained model to a specific labeled dataset.

2

Parameter-Efficient Fine-Tuning (PEFT)

Methods like LoRA for fine-tuning LLMs with minimal computation.

3

Instruction Tuning

Fine-tuning on a collection of tasks described by natural language instructions.

4

Prompt Engineering

Designing effective prompts to guide LLM behavior, including Chain-of-Thought.

GeekDost - Roadmaps & Snippets for Developers