What inference optimizations for standard LLM can be suggested if the corporate GPT is running slowly?
Machine Learning / AI
What do you think about this work scheme (outstaff through Aston on the VTB project)?
What are the features of label noise robust training?
What is a video-language model (VideoLLaMA, Video-ChatGPT)?
What is the difference between boosting and bagging (Random Forest)? Compare their tendency to overfit.
What metrics are used for segmentation and object detection?
What is distant supervision (NER from KB)?
Why won't a linear model without feature transformation solve the problem of separating points inside and outside a circle?
What is the asymptotic complexity of multiple passes through a list?
What is DeepAR from Amazon?
What are the uplift use cases in marketing (target population)?
What are the types of regularization and how do they work?
How to get a deadlock for experiments?
How was the chunking strategy chosen for the RAG system?
How to choose the size of embedding vectors?
Have you encountered Liquibase?
Tell us about bag-of-words and its limitations.
What is a cure model?