Question 1 of 8
Self-attention lets a transformer:
Question 2 of 8
Why do transformers need positional encodings?
Question 3 of 8
A language model's context window is:
Question 4 of 8
Retrieval-augmented generation (RAG) reduces hallucination by:
Question 5 of 8
Raising the sampling temperature makes output:
Question 6 of 8
Tokens are:
Question 7 of 8
Fine-tuning is usually the wrong tool when you need:
Question 8 of 8
An embedding is:
0/8 answered