Zenaique
Topics
Practice
Browse
Reference
Challenges
Pricing
Search…
⌘K
Topics
/
Attention Mechanism
/
Head Dim
Head Dim
Subtopic
3 questions
Questions tagged with Head Dim — part of Attention Mechanism.
Format
Difficulty
Role
Experience
Sort
Newest
Quality
Difficulty ↑
Difficulty ↓
Questions
Name the scalar that QK^T is divided by inside scaled dot-product attention.
Flashcard
Easy
·
Qual 4.0
Pick the formula that defines head_dim from hidden_size and num_heads.
Multiple Choice
Easy
·
Qual 4.0
Modern 7B-class LLMs, fill in typical head counts and the resulting per-head dimension
Fill in Blank
Easy
·
Qual 4.0