sshh12 / multi_token

Embed arbitrary modalities (images, audio, documents, etc) into large language models.

sshh12/multi_token Issues

is the training data available?
Closed a month ago2
Supported Base Models
Closed a month ago1
Summarize video
Closed a month ago1
pretrain errors
Updated 2 months ago4
Adapter weights not found
Updated 2 months ago9
HFValidationError
Closed 2 months ago
can you share an dataset to me use to train my vision model based on this?
Closed 3 months ago3
Thanks for the great work
Closed 3 months ago4
Thank you for posting this!
Closed 3 months ago3
Require ``ModalityArguments`` for new modalities
Closed 4 months ago3
wait, what is that in my training?
Closed 5 months ago1
theres nothing in my output
Closed 5 months ago7
Finetuning already trained model
Closed 5 months ago2
Multiple Image QA Model
Closed 6 months ago3