self-distillation
Latest stories covering self-distillation, with summaries and links to related coverage.
1 articles · page 1 of 1
Connected topics
Apple: Embarrassingly Simple Self-Distillation Improves Code Generation
research
2 min read
Self-distillation (SSD) enables large language models to enhance code generation by using their own raw outputs without the need for a verifier or teacher model. The process involves sampling solutions with specific temperature and truncation settings, followed by fine-tuning.