C.W.K.
Stream
Quiz · 4 questions

🌳 Model Families

GPT, Llama, Mistral, Claude, Gemini, and the alternatives

Level 0Token
0 XP0/94 lessons0/10 achievements
0/120 XP to next level120 XP to go0% complete

Quiz

01What is the key architectural difference between encoder-only (BERT) and decoder-only (GPT) models?
Hint
It's about which tokens each token can attend to.
02How many total parameters does Llama 4 Maverick have?
Hint
It's the larger of the two main Llama 4 variants — Scout vs this one.
03What is Mamba's key architectural difference from Transformers?
Hint
It's a fundamentally different way of mixing information across the sequence axis.
04What context window does Gemini 2.5 Pro support?
Hint
It's the same as Gemini 1.5 Pro's launch context.
Spotted a bug or have feedback on this page?Report an Issue

Comments 0

🔔 Reply notifications (sign in)
Sign inPlease sign in to comment.

No comments yet — be the first.