-
Notifications
You must be signed in to change notification settings - Fork 10
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
有个bug运行不起来 #8
Comments
Hi,感谢你对我们工作的关注和提问。因为我们默认CogCoM是一个针对图像的多模态模型,所以在训练时没有考虑输入不包含图像的情况。然而,你可以通过将
然而需要注意的是,我们目前的模型版本在多模态训练阶段没有纯文本样本(在上下文窗口中mask掉),所以经过测试发现在纯文本输入的情况下模型的回复效果较差。需要通过结合纯文本的微调来缓解,关于微调可以参考 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
我注意到你们chat.py文件里面219行:
get_func = text_processor.get_func(inputs, **inputs_dic) if hasattr(text_processor, 'get_func') else get_masks_and_position_ids_default
可是如果我一开始没有输入图,image_position < 5,那么inputs_dic不会被赋值text_processor(new_prompt) (205行),就会报错“在变量定义之前使用”
请问这个怎么解决啊,谢谢
The text was updated successfully, but these errors were encountered: