text-generation-inference
text-generation-inference copied to clipboard
huggingface
Qwen2-VL
Model description
Open source status
- [X] The model implementation is available
- [X] The model weights are available
Provide useful links for the implementation
https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct https://qwenlm.github.io/blog/qwen2-vl/ https://github.com/QwenLM/Qwen2-VL
Hi @jvhgit 👋
Thanks for opening the issue. Could you provide a bit more context, are you requesting for this model to be added?
Hi, yes I am requesting this model (family) to be added. I think it is powerfull multimodal model based on my (basic) tests. Also, the license is apache 2.0 which makes it commercially permissive to run.
Awesome, thank's for clarifying!
We don't have at the moment a lot of extra bandwidth but we might prioritize adding this model.
Also as a note, to indicate more demand for a model getting thumbs ups or similar reactions on your issue is a signal for us to prioritize something :)
Hi, It seems that this issue got some traction. In my team we see real value to use this model and its finetunes for production. Are there any updates concerning the support this model? Kind regards,
@jvhgit this is being worked on 🙌 can't promise a timeline but hopefully soon 🤞
@ErikKaum thank you for your reply and good to hear this is being worked on. Keep up the good work!
Hi @ErikKaum , is this model already implemented? I tried deploying it yesterday, and while the startup works fine, I encountered some inference issues (which are expected if the mode isn't fully supported yet).
Hi @maxjeblick 👋
The model should work and be implemented. Could you open an issue such that the team can reproduce the bug?
Closing since it's supported in: https://github.com/huggingface/text-generation-inference/releases/tag/v2.4.1