Training project

Parameter-efficient LLM fine-tuning lab

Related course: LLM Fine-Tuning

Problem

Learners practice dataset prep and LoRA/PEFT-style fine-tuning rather than only prompting a frozen model.

Architecture (high level)

Dataset formatting → tokenizer config → LoRA/Adapters training with Transformers/PyTorch → basic evaluation as covered in the LLM Fine-Tuning syllabus.

Technologies

  • Hugging Face
  • PyTorch
  • LoRA
  • Transformers

This is a Vector Skill Academy training project completed during the course. It is not confidential client work and does not represent a live production engagement.