Closed xiaoToby closed 7 months ago
finetune之后的模型(output/checkpoint-400)生成的是lora,需要和原始模型合并使用,你把原模型删了,肯定出错啊。
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your consideration.
Closing the issue, since no updates observed. Feel free to re-open if you need any further assistance.
提交前必须检查以下项目
问题类型
模型训练与精调
基础模型
Chinese-LLaMA-2 (7B/13B)
操作系统
None
详细描述问题
使用finetune之后的模型(output/checkpoint-400),把finetune前的原始模型删掉后,运行失败。因为在adapter_config.json文件中有base_model_name_or_path,运行finetune之后的模型还是会读取这个路径,报OSError: Can't load the configuration of ‘xxx’错误。 我的问题是,因为想在容器环境内运行,不想让容器太辎重了,所以删掉了原始模型,我想问为什么还是会要读取原始模型?
依赖情况(代码类问题务必提供)
运行日志或截图