Prince Canuma
Prince Canuma
Not yet. It's one of the things want to add next. My focus at the moment is on the trainer and new models (pixtral, llama and molmo)
It would be awesome if you could implement this I would be more than happy to help, review and merge the PR🚀
I think this will be easier and faster to do after I release prompt caching. That way you only are computing KV for the last message only.
Hey guys, I thought a about it and here is an example that you could use to build this use case. I will work on a more robust example, showcase...
Example output:
Yes there is :)
@softwaredoug try Pixtral, Qwen2VL, Idefics 3, SmolVLM or llava-interleave
Closing stale
Thanks @mattjcly ! I have streamline a way to resize images here #83. Now, regarding your buffer size. Do you have a suggested default you would like to use? Or...
I'm not sure about step 2 either. Let me check.