Skip to content
New issue

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

运行baseline时replug和ircot报错 #96

Open
ChangWang9 opened this issue Nov 6, 2024 · 2 comments
Open

运行baseline时replug和ircot报错 #96

ChangWang9 opened this issue Nov 6, 2024 · 2 comments

Comments

@ChangWang9
Copy link

把generator改成远程gpt的模型后,进行baseline测试时,replug和ircot发生了不同类型的报错
replug报错
OSError: gpt-4o-mini is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' If this is a private repository, make sure to pass a token having permission to this repo either by logging in with huggingface-cliloginor by passingtoken=<your_token>
ircot报错flashrag/prompt/base_prompt.py", line 57, in truncate_prompt
assert isinstance(prompt, list)
AssertionError
`
数据集用的都是hotpotqa,不太清楚怎么解决(其余一些方法可以跑通)

@ignorejjj
Copy link
Member

gpt-4o-mini得用调用api的方式来调用,可以把framwork换成openai,然后进行对应的设置

@ChangWang9
Copy link
Author

ChangWang9 commented Nov 13, 2024

gpt-4o-mini得用调用api的方式来调用,可以把framwork换成openai,然后进行对应的设置

已解决,谢谢,目前在进行IRCoT方法的baseline测试,有个问题想要请教一下,在baseline_details_zh.md中提到"对于所有实验,我们使用一次示例来添加提示",发现用项目中的原设置,generator改为gpt-4o-mini后,在2wikimultihopqa上进行测试,发现常常答非所问,回答的都是示例中的问题,很奇怪

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants