Zenaique
Topics
Practice
Browse
Reference
Challenges
Pricing
Search…
⌘K
Topics
/
Attention Mechanism
/
D Head
D Head
Subtopic
2 questions
Questions tagged with D Head — part of Attention Mechanism.
Format
Difficulty
Role
Experience
Sort
Newest
Quality
Difficulty ↑
Difficulty ↓
Questions
True or false: switching from 1-head to 12-head attention at the same d_model increases total parameter count.
Multiple Choice
Medium
·
Qual 4.0
If d_model = 768 and num_heads = 12, what is d_head?
Fill in Blank
Easy
·
Qual 4.0