Multimodal model opensource

#1
by YangJiassh - opened

Hello, I'd like to know if you have any plans to open-source your multimodal model architecture? I would like to try local inference to see the results. Thank you.

Same issue, looks like only wieghts is meaningless.

When will you release the technical report about the InternOmni? I want to know the training detail about the sequence between audio and image.

Sign up or log in to comment