Transformers and Large Language Models
Pretraining, Fine-Tuning, Generation, and the KV Cache
Distinguish model training from generation and analyze the resources inference requires.
0/7Articles read
0/21Latest correct answers
21Unanswered questions
0Due for review
Loading learning records…
Readings and practice
Pretraining, Fine-Tuning, Generation, and the KV Cache
Unread · Latest correct 0/3
Practise these questionsAnswer history and review dates
Question 1
Not yet answered
Question 2
Not yet answered
Question 3
Not yet answered
Calculating KV-cache capacity
Unread · Latest correct 0/3
Practise these questionsAnswer history and review dates
Question 1
Not yet answered
Question 2
Not yet answered
Question 3
Not yet answered
Calculating KV-cache size from model configuration
Unread · Latest correct 0/3
Practise these questionsAnswer history and review dates
Question 1
Not yet answered
Question 2
Not yet answered
Question 3
Not yet answered
Context windows
Unread · Latest correct 0/3
Practise these questionsAnswer history and review dates
Question 1
Not yet answered
Question 2
Not yet answered
Question 3
Not yet answered
Separating prefill and decode in LLM inference
Unread · Latest correct 0/3
Practise these questionsAnswer history and review dates
Question 1
Not yet answered
Question 2
Not yet answered
Question 3
Not yet answered
Encoder versus decoder models
Unread · Latest correct 0/3
Practise these questionsAnswer history and review dates
Question 1
Not yet answered
Question 2
Not yet answered
Question 3
Not yet answered
RAG versus fine-tuning
Unread · Latest correct 0/3
Practise these questionsAnswer history and review dates
Question 1
Not yet answered
Question 2
Not yet answered
Question 3
Not yet answered