Skip to main content
🔒 Preview mode. The first 15 Foundations lessons are free; this one is Pro. Start a 7-day trial to unlock the editor, AI hints and the rest of the curriculum. Card required, cancel any time in Dashboard.
Start 7-day trial →
⚡
← Courses
›
Data Science Applied
›
Module 6 · Deep Learning + MLOps
›
Fine-tuning: full vs LoRA
quiz
91 / 104
🇺🇸
EN
▼
↗
Share
⋯
More
+100 XP
📋
Task
📖
Theory
🤖
AI Help
Task
📝 **Question:** Right approach for adapting a 70B model on 10k examples? 📋 Pick the right answer. 💡 **Hint:** Re-read the theory above if unsure.
🎯 Quiz
Question
📝 **Question:** Right approach for adapting a 70B model on 10k examples? 📋 Pick the right answer. 💡 **Hint:** Re-read the theory above if unsure.
A
Full fine-tune — 10k labeled examples is large enough to update every weight without serious overfitting risk.
B
LoRA — adds <1% parameters, fits on consumer hardware, near-full quality.
C
Prompt-tuning only — learn 100 soft tokens prepended to inputs; cheapest possible and matches LoRA on small datasets.
D
Pre-train from scratch on the domain corpus — distilling 70B down to a 7B domain model beats any adapter approach.
Submit answer
💬 Discussion
Be the first to ask a question or share a tip.
Sign in
to join the discussion. Reading is free.
Loading discussion…