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

DeepSeek-Janus-Pro-7B模型测试chat前端无响应 #375

Open
Yu-Zhouz opened this issue Feb 21, 2025 · 7 comments
Open

DeepSeek-Janus-Pro-7B模型测试chat前端无响应 #375

Yu-Zhouz opened this issue Feb 21, 2025 · 7 comments

Comments

@Yu-Zhouz
Copy link

Yu-Zhouz commented Feb 21, 2025

我使用gguf/DeepSeek-Janus-Pro-7B作为模型后端的服务,
测试
`
import vision_agent.tools as T
import matplotlib.pyplot as plt

image = T.load_image("/home/VisionAgent/examples/chat/tmp4vcajy48.png")
dets = T.countgd_object_detection("person", image)
viz = T.overlay_bounding_boxes(image, dets)

T.save_image(viz, "people_detected.png")

plt.imshow(viz)
plt.show()

`
已经测试成功
输入输出图像分别为:

Image

Image

但是前端export/chat测试无响应结果

Image

@ld-xy
Copy link

ld-xy commented Feb 24, 2025

老哥,可以咨询你一些事情吗?就是你说的更换大语言模型,是如何实现的啊,我就看见更换config配置文件,配置文件里如何设置还有apikey设置到哪里?希望可以回复一下,感谢感谢

@Yu-Zhouz
Copy link
Author

老哥,可以咨询你一些事情吗?就是你说的更换大语言模型,是如何实现的啊,我就看见更换config配置文件,配置文件里如何设置还有apikey设置到哪里?希望可以回复一下,感谢感谢

您好,请给我发送邮件或者提供你的联系方式我可以把修改后代码的版本发送给你

@Mrguanglei
Copy link

@Yu-Zhouz 哥,我也需要一下。[email protected]

@Tsai-chasel
Copy link

请教如何实现,希望可以回复一下,感谢感谢
邮箱tsaichasel@outlook@com

@ld-xy
Copy link

ld-xy commented Feb 25, 2025

老哥,可以咨询你一些事情吗?就是你说的更换大语言模型,是如何实现的啊,我就看见更换config配置文件,配置文件里如何设置还有apikey设置到哪里?希望可以回复一下,感谢感谢

您好,请给我发送邮件或者提供你的联系方式我可以把修改后代码的版本发送给你

老哥老哥,[email protected],感谢感谢

@Yu-Zhouz
Copy link
Author

请教如何实现,希望可以回复一下,感谢感谢 邮箱tsaichasel@outlook@com

https://blog.csdn.net/weixin_62828995/article/details/145851969?sharetype=blogdetail&sharerId=145851969&sharerefer=PC&sharesource=weixin_62828995&spm=1011.2480.3001.8118

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

4 participants