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

咨询,是否有完成从qwen2-vl-0.5B升级到qwen2-vl-7B的经验分享一下,谢谢 #216

Closed
evanlin88 opened this issue Nov 14, 2024 · 4 comments

Comments

@evanlin88
Copy link

evanlin88 commented Nov 14, 2024

GOT-OCR2.0 使用 ViTDet-80M 和Qwen-0.5B,是否除了升级Qwen2-vl-7B外,还需升级ViTDet?

@Ucas-HaoranWei
Copy link
Owner

不需要吧,换7B感觉也没必要,太大了吧

@evanlin88
Copy link
Author

不需要吧,换7B感觉也没必要,太大了吧

因为试用了qwen2-vl-7b的ocr识别功能,感觉不错,但速度是慢了,本来想用7B的样本量来提升识别能力。目前自己造的样本量,质量和数量都不高,才几千张,

@xlg-go
Copy link

xlg-go commented Nov 15, 2024

不需要吧,换7B感觉也没必要,太大了吧

因为试用了qwen2-vl-7b的ocr识别功能,感觉不错,但速度是慢了,本来想用7B的样本量来提升识别能力。目前自己造的样本量,质量和数量都不高,才几千张,

#217

您好,请教一下,这个ocr纠错你遇到过吗?

@evanlin88
Copy link
Author

不需要吧,换7B感觉也没必要,太大了吧

因为试用了qwen2-vl-7b的ocr识别功能,感觉不错,但速度是慢了,本来想用7B的样本量来提升识别能力。目前自己造的样本量,质量和数量都不高,才几千张,

#217

您好,请教一下,这个ocr纠错你遇到过吗?

我这边微调后的效果也会有纠错的,哈,识别:I have apple

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

3 participants