UNIT 016 h allocated
Adaptation choices
- Prompting
- retrieval
- fine-tuning
- task suitability
← Course catalogue
LANGUAGE & GENERATIVE AI / SPECIALIST
NLP330Language-model adaptation & efficient fine-tuning
24 h productive allocation9 h 36 m learning + 14 h 24 m training4 units · 1 assessed practical brief
Detailed course plan and training brief. A complete taught course pack is in preparation. The linked foundation module, where shown, is a smaller available resource.
BEFORE YOU BEGIN
A clear starting point.
Specialist studio; environment and faculty must be confirmed before scheduling
WHAT YOU SHOULD BE ABLE TO DEMONSTRATE
- Explain the assumptions and failure modes in adaptation choices.
- Complete the practical: adapt a small permitted model or compare prompting with adaptation on an explicit held-out task.
- Defend the resulting data card with reproducible evidence.
THE SUBJECTS / FOUR CONNECTED UNITS
What you will study.
UNIT 026 h allocated
Training data
- Instruction data
- filtering
- contamination
- evaluation splits
UNIT 036 h allocated
Efficient adaptation
- Low-rank adaptation
- quantisation concepts
- memory
- training budgets
UNIT 046 h allocated
Evaluation
- Held-out tasks
- regression tests
- refusal
- cost-quality trade-offs
THE TRAINING STUDIO
Make the subject
visible in your work.
Adapt a small permitted model or compare prompting with adaptation on an explicit held-out task.
Evidence to produce
- Data card
- adaptation configuration
- task evaluation
- resource record
Training brief for supervised delivery. Code, datasets, answer keys and environment acceptance must be completed in the full course pack before delivery is confirmed.
ASSESS THE REASONING
A question you
should be able to answer.
When is fine-tuning the wrong response to missing factual knowledge?
Review dimensions
Technical correctness · reproducibility · interpretation of results · failure analysis · individual explanation. Course-level rubric and faculty moderation form part of the final adopted teaching pack.
External reference access, hardware, cloud accounts and paid services are separate. No third-party certification is included by implication.