We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
No response
readme里面给出了三种微调的方法,其中两种微调的评估代码也给在了仓库里,但是缺少对未微调的原始模型进行评估的脚本
个人简单看了看代码,想要测试原始模型于是尝试了几个命令行参数的组合,发现去除了--pre_seq_len后似乎会选择运行全量微调(或者其评估),由于显存不够没能成功运行。 同时我还发现似乎在p-tuning的设置中修改checkpoint的路径,能够运行一个疑似对原始模型进行的评估,生成的结果有些类似于直接运行模型进行生成的响应,想要和编写main.py代码的小伙伴确认一下我的想法是否正确,这种方式是不是在对原始模型进行评估
--pre_seq_len
顺便问一下 fine-tuning的代码没法在量化模型下运行,Python会报类型不匹配的错误,这个也符合预期吗,还是说代码有待改进? No response
The text was updated successfully, but these errors were encountered:
No branches or pull requests
Is your feature request related to a problem? Please describe.
No response
Solutions
readme里面给出了三种微调的方法,其中两种微调的评估代码也给在了仓库里,但是缺少对未微调的原始模型进行评估的脚本
个人简单看了看代码,想要测试原始模型于是尝试了几个命令行参数的组合,发现去除了
--pre_seq_len
后似乎会选择运行全量微调(或者其评估),由于显存不够没能成功运行。同时我还发现似乎在p-tuning的设置中修改checkpoint的路径,能够运行一个疑似对原始模型进行的评估,生成的结果有些类似于直接运行模型进行生成的响应,想要和编写main.py代码的小伙伴确认一下我的想法是否正确,这种方式是不是在对原始模型进行评估
Additional context
顺便问一下 fine-tuning的代码没法在量化模型下运行,Python会报类型不匹配的错误,这个也符合预期吗,还是说代码有待改进?
No response
The text was updated successfully, but these errors were encountered: