What are A2C and A3C?
Machine Learning / AI
Task: what is more efficient in terms of speed — submitting 2 inputs of 512 tokens each to the transformer separately (2x512) or combining them into 1x1024?
What methods exist for reducing the size of a model while maintaining quality?
How many rows will CROSS JOIN return for tables with 100 and 10 records?
What is Retrieval-Augmented Generation? What components does it consist of?
What is GPTQ and what is the approach to weight selection?
Calculate the probability that all results are unique when rolling a six-sided die six times?
What parts does Stable Diffusion (SD) consist of?
What is ShuffleNet and why is channel shuffle used there?
How to display information about how much video memory each process occupies in Linux?
How to organize A/B testing to evaluate the effectiveness of a widget?
What is Named Entity Recognition (NER)? What annotation is most commonly used (BIO, BIOES)?
What is the complexity of analytical solutions for linear regression and when is it unstable?
What is hierarchical forecasting and reconciliation?
What is a key-value database?
What is STL decomposition?
How to detect that a model is hallucinating and not using context?