When trying to reproduce the example for video retrieval from https://huggingface.co/Tevatron/OmniEmbed-v0.1 and copy pasting the entire code, I get ValueError: Videos features and imagve tokens do not match: tokens: 0, features 16744.. Is the HF implementation broken? I am using transformers version 4.56.2 and torch version 2.8.0.
The same goes for the example on image document retrieval. When trying to reproduce the HF example, I am getting ValueError: Image features and image tokens do not match: tokens: 0, features 1290.
When trying to reproduce the example for video retrieval from https://huggingface.co/Tevatron/OmniEmbed-v0.1 and copy pasting the entire code, I get
ValueError: Videos features and imagve tokens do not match: tokens: 0, features 16744.. Is the HF implementation broken? I am using transformers version 4.56.2 and torch version 2.8.0.The same goes for the example on image document retrieval. When trying to reproduce the HF example, I am getting
ValueError: Image features and image tokens do not match: tokens: 0, features 1290.