Back to questions
QuestionHardProduct CasesTechnical interview · inDrive

Attention, positional embeddings, BPE, and LoRA

Explain scaled dot-product attention, why Transformers need positional embeddings, how BPE tokenization works, and what LoRA changes during fine-tuning.

Answer as you would in an interview

Answer aloud or write down a few key points. The text field is optional; the review opens after your attempt.

Loading
Attention, positional embeddings, BPE, and LoRA — interview question — ML Mentor