Meta’s System 2 Distillation Technique for Llama 2 Dialog Models
When discussing strategies for large language models (LLMs), there are generally two types: System 1 (fast reaction) and System 2 (slow thinking). System 2 reasoning tends to involve more deliberate thought, generating intermediate reasoning that allows the model (or human) to reason and plan in order to successfully complete tasks or respond to instructions. Effortful … Read more