Quick Overview

This question evaluates proficiency in preprocessing for autoregressive language models, including deterministic sequence packing, construction of loss masks, segment range bookkeeping, answer span localization, and handling truncation and padding edge cases.

Implement SFT Sample Packing

Company: Microsoft

Role: Machine Learning Engineer

Category: Coding & Algorithms

Difficulty: medium

Interview Round: HR Screen

Quick Answer: This question evaluates proficiency in preprocessing for autoregressive language models, including deterministic sequence packing, construction of loss masks, segment range bookkeeping, answer span localization, and handling truncation and padding edge cases.

Loading…