Replies: 16 comments
-
基础作业构建数据集，使用 XTuner 微调 InternLM-Chat-7B 模型, 让模型学习到它是你的智能小助手。 微调前（回答比较官方） 微调后（对自己的身份有了清晰的认知） |
Beta Was this translation helpful? Give feedback.
-
|
基础作业 微调前（回答比较官方） 微调后（对自己的身份有了清晰的认知） |
Beta Was this translation helpful? Give feedback.
-
|
基础作业： |
Beta Was this translation helpful? Give feedback.
-
|
https://h90ag9106t.feishu.cn/docx/YjQPdpEJpohTe8xF2UucCguanbe |
Beta Was this translation helpful? Give feedback.
-
|
原计划训练为3次，但训练第1次后，损失已经很低，且由于学习实践整体流程，一定过拟合，无需消耗第2和3次时间。 结果如下图 |
Beta Was this translation helpful? Give feedback.
-
作业使用脚本处理python官方doc txt版本的FAQ，生成json，一起加入finetune |
Beta Was this translation helpful? Give feedback.
-
|
|
Beta Was this translation helpful? Give feedback.
-
|
基础作业 微调后（对自己的身份有了清晰的认知） |
Beta Was this translation helpful? Give feedback.
-
|
InterLM L-4: XTuner 大模型单卡低成本微调 基础作业打卡~ |
Beta Was this translation helpful? Give feedback.
-
|
基础作业 |
Beta Was this translation helpful? Give feedback.
-
|
微调前： |
Beta Was this translation helpful? Give feedback.
-
|
https://github.com/RyanWu31/tutorial_notebook/blob/main/README.md |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
|
做了点有趣的东西 |
Beta Was this translation helpful? Give feedback.
-
|
|
Beta Was this translation helpful? Give feedback.
-
|
|
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
在下方讨论区提交作业（图片/链接形式均可）~
基础作业
构建数据集，使用 XTuner 微调 InternLM-Chat-7B 模型, 让模型学习到它是你的智能小助手，效果如下图所示，本作业训练出来的模型的输出需要将不要葱姜蒜大佬替换成自己名字或昵称！
微调前（回答比较官方）
微调后（对自己的身份有了清晰的认知）
作业参考答案：https://github.com/InternLM/tutorial/blob/main/xtuner/self.md
进阶作业：
Beta Was this translation helpful? Give feedback.
All reactions