Transformer Models Insights
Yannic and Connor discuss the strengths of transformer models like Bert and GPT-2 in handling longer context windows and bi-directional processing. They explore the trade-offs between attending to every position in text and hierarchical structures, shedding light on the challenges of language modeling.In this clip
From this podcast
Machine Learning Street Talk (MLST)
OpenAI GPT-3: Language Models are Few-Shot Learners
Related Questions