New Features

[zhangce]

Thanks visarga for the suggestion:

https://news.ycombinator.com/item?id=38077521

• summary, for better topic embedding
• named entities, for knowledge base
• implicit tasks present in the text, what are the tasks a LLM could learn from a given example?
• chain-of-thought augmentation, to bring out implicit deductions; it has been shown in the Phi-1.5 paper and Orca that synthetic CoT datasets are superior source materials