Missing arguments in processor
Dear All,
When running the demo code from the model page, I got the warning:
Expanding inputs for image/video tokens in LLaVa-NeXT-Video should be done in processing. Please add patch_size and vision_feature_select_strategy to the model's processing config or set directly with processor.patch_size = {{patch_size}} and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47.
It was because the processor was not correctly set. Patch_size and vision_feature_select_strategy should not be null. But I got:
I found that the processor is loaded from processor_config.json. But why this file is missing?
My transformers version is 4.46.2
@chocoded
will be updating the configs this week, in the meanwhile you can set them yourself topatch_size = model.config.vision_config.patch_size and
vision_feature_select_strategy = model.config.vision_feature_select_strategy
Thanks. This works for me.