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.

Sign up for GitHub

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

Jump to bottom

[Feature request] Add support/demo implementation for Qwen-VL GGUF model #497

Open
CoruNethron opened this issue Aug 30, 2023 · 2 comments
Open

[Feature request] Add support/demo implementation for Qwen-VL GGUF model #497

CoruNethron opened this issue Aug 30, 2023 · 2 comments

Comments

@CoruNethron
Copy link

Hello. May be this can be interesting for future roadmap:
https://github.com/QwenLM/Qwen-VL

It is multimodal and multilangual 7B model, able to analyze image, including text recognition and compare two (at least) images. Also able to detect bounding box of an object within image.

Seems, like it also beats some very good 13B models in pure textual context.

photo_2023-08-30_04-40-45

Would be nice to see it running quantized in GGUF.
@CoruNethron
Copy link
Author

Closing this, as Qwen inference has being added few days ago:
https://github.com/QwenLM/qwen.cpp

@CoruNethron
Copy link
Author

Sorry for increasing entropy here, just realized, that recently implemented inference is for another model:
https://github.com/QwenLM/Qwen
vs
https://github.com/QwenLM/Qwen-VL
So, I reopen this feature request.

@CoruNethron CoruNethron reopened this Oct 17, 2023
CCLDArjun pushed a commit to CCLDArjun/ggml that referenced this issue Dec 18, 2023
@anzz1
CMake / CI additions (ggerganov#497)
2f7bf7d 
* CMake: Add AVX512 option

* CI: Add AVX/AVX512 builds (Windows)
(AVX512 tests can only be run when the worker happens to support it, building works anyway)

* CMake: Fix sanitizer linkage ( merged ggerganov#468 )

* CI: Add sanitizer builds (Ubuntu)

* CI: Fix release tagging
(change @zendesk/action-create-release to @anzz1/action-create-release until upstream PR Added commitish as input zendesk/action-create-release#32 is merged)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@CoruNethron