rhelck

@zucchini-nlp I'm seeing the following problem File "/home/rhelck/videotest.py", line 3, in from transformers import VideoLlavaProcessor, VideoLlavaForConditionalGeneration ImportError: cannot import name 'VideoLlavaProcessor' from 'transformers' (/home/rhelck/videovenv/lib/python3.10/site-packages/transformers/__init__.py) The older example works fine for...

@zucchini-nlp That worked perfectly, thanks!

@rovebot Did you try to set the device_map ?

You can specify device_map = {"",0} to load everything on the same CUDA device in main.py @827648313