Is this a newer/better model than OneVision?
#1
by ehayes-haiper - opened
Title
Yes. In terms of video. It is a video specific model
Thanks! Is inference the same as llava-OneVision? I.e. all the same tokens, dimensions etc?
Almost the same.
Title
Yes. In terms of video. It is a video specific model
Thanks! Is inference the same as llava-OneVision? I.e. all the same tokens, dimensions etc?
Almost the same.