LLM
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/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:
- 将 175 个人工设计的指令任务作为种子,使用 text-davinci-003 随机生成指令,最终生成了 52,000 条指令数据。例如:
{"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
LLM
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/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:
- 将 175 个人工设计的指令任务作为种子,使用 text-davinci-003 随机生成指令,最终生成了 52,000 条指令数据。例如:
{"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