AlpaGasus: Training A Better Alpaca with Fewer Data · HackerPapers discussions

AlpaGasus: Training A Better Alpaca with Fewer Data — mentioned by isaacfung

Fri, 22 Sep 2023 11:37:17 GMT

LIMA: Less Is More for Alignment https://arxiv.org/abs/2305.11206 AlpaGasus: Training A Better Alpaca with Fewer Data https://arxiv.org/abs/2307.08701 Textbooks Are All You Need II: phi-1.5 technical report https://arxiv.org/abs/2309.05463 Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models https://arxiv.org/abs/2307.14430

Paper and discussion history. A mention is not an endorsement.

AlpaGasus: Training A Better Alpaca with Fewer Data — mentioned by isaacfung

Mon, 18 Sep 2023 05:25:16 GMT

Quality matters just as much as quantity. LIMA: Less Is More for Alignment https://arxiv.org/abs/2305.11206 AlpaGasus: Training A Better Alpaca with Fewer Data https://arxiv.org/abs/2307.08701 Textbooks Are All You Need II: phi-1.5 technical report https://arxiv.org/abs/2309.05463

Paper and discussion history. A mention is not an endorsement.