斯坦福的 Alpaca 模型基于 LLaMA-7B 和指令微调,仅使用约 5 万条训练数据,就能达到类似 GPT-3.5 的效果。
斯坦福70亿参数开源模型媲美GPT-3.5,100美元即可复现mp.weixin.qq.com/s/U6ioEygg5mlVpAIb2L3cZw正在上传…重新上传取消
Alpaca 的训练流程很简单,只有两个步骤:
{
"instruction": "Rewrite the following sentence in the third person",
"input": "I am anxious",
"output": "She is anxious."
}, {
"instruction": "What are the three primary colors?",
"input": "",
"output": "The three primary colors are red, blue, and yellow."
},
2. 用指令数据