What prompt compression techniques do you know (LLMLingua)?
Machine Learning / AI
What is TF-IDF?
How to determine the derivative of the loss function for log loss and MSE?
Move zeros to the end of the array, preserving the order of the other elements [1, 0, 8, 9] -> [1, 8, 9, 0] def move_zeros(nums: list[int]): pass
What is Rainbow DQN and what components does it combine?
What is data versioning and how does it compare DVC, LakeFS, lakeFS?
What is Tesseract and where are its quality limits?
How to determine if an embedding model performs well? What metrics are used?
Where did the new weights come from and why are there more of them?
What fallback methods are there in case of no internet and weak device?
What is a replica and shard in a distributed VDB?
How is the step t sampled during training and inference in Stable Diffusion?
How to organize data storage considering data from multiple sources: backend databases, clickstream, CRM, and communications?
How is the correlation matrix calculated?
What work format do you prefer — office, remote, team, or independent work?
What is the MAP metric?
How do you evaluate the readiness of a support ticket classification system for deployment?
Have you ever dealt with recommendation systems?
Tell how the clustering algorithm you used worked — how did it aggregate points in space?
How quickly can you be ready to start a new job?