Alpaca: A Strong, Replicable Instruction-Following Model

作者： Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, Tatsunori B. Hashimoto (2023)

TLDR（中文）

用 52K 条 self-instruct 数据 + LLaMA 7B，5 美元复刻 GPT-3.5 风格回答。开启开源指令微调浪潮，是 2023 年那场"羊驼大战"的起点。

TLDR (English)

Uses 52K self-instruct data + LLaMA 7B to replicate GPT-3.5 style responses for $5. Launched open-source instruction tuning wave, starting point of 2023's "llama wars".