How to use Alpha-VLLM/Lumina-mGPT-7B-512-MultiImage with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSeq2SeqLM processor = AutoProcessor.from_pretrained("Alpha-VLLM/Lumina-mGPT-7B-512-MultiImage") model = AutoModelForSeq2SeqLM.from_pretrained("Alpha-VLLM/Lumina-mGPT-7B-512-MultiImage", device_map="auto")
Sorry, this is an image-text to image-text model, but there doesn't seem to be such an option. What's your suggestion?
@Cxxs I have decided to add a task called any-to-any to Hub, so I think for now we can close this PR.
any-to-any
· Sign up or log in to comment
