Zenaique
Topics
Practice
Browse
Reference
Challenges
Pricing
Search…
⌘K
Topics
/
Fine-Tuning
/
Attention Mask
Attention Mask
Subtopic
6 questions
Questions tagged with Attention Mask — part of Fine-Tuning.
Format
Difficulty
Role
Experience
Companies
Sort
Newest
Quality
Difficulty ↑
Difficulty ↓
Questions
Spot the bug: packed-sequence SFT where the model learns to copy across unrelated examples
Spot the Error
Hard
·
Qual 4.0
DataCollator pads to max_length and sets attention_mask = ones: find what breaks
Spot the Error
Medium
·
Qual 4.0
Predict what softmax produces when every key in a row is masked out.
Spot the Error
Medium
·
Qual 4.0
You pad a batch to equal length. How does the model know to ignore the filler tokens?
Flashcard
Easy
·
Qual 4.0
Spot the bug in this sequence-packing setup
Spot the Error
Hard
·
Qual 4.0
Sequence packing: what it does, and the attention-mask gotcha
Short Answer
Hard
·
Qual 4.0