lmms-lab

/

llava-next-interleave-qwen-7b-dpo

like 9

Hi,
I starting reading through your demo, but the pipeline is (understandably) tightly integrated with gradio. Would it be possible to get a minimal example of how to run the model using a tokenizer, image processor and the model object? Preferably both for getting next token logits and generation :) thanks!