nvidia
/

NVLM-D-72B

Image-Text-to-Text

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (7)

How to use NVLM only for text task? [wrong pixel_values size: torch.Size([1, 5])]

#28 opened 3 days ago by

How to run NVLM with AI Agents

#27 opened 8 days ago by

{"message":"unknown or invalid runtime name: nvidia"}

#26 opened 10 days ago by

Cannot run inference: got multiple values for keyword argument 'return_dict'

#25 opened 18 days ago by

nvidia

#24 opened 20 days ago by

Running the model in 'cpu'

#22 opened about 1 month ago by

dfgdfg

#20 opened about 1 month ago by

License

#19 opened about 1 month ago by

Can not host as vLLM ?

#17 opened about 1 month ago by

Inference Error: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0

#14 opened about 2 months ago by

space or lmarena to test it online

#13 opened about 2 months ago by

Request: DOI

#12 opened about 2 months ago by

Apple Metal GPU

#11 opened about 2 months ago by

low memory usage

#10 opened about 2 months ago by

Upload 5 files

#9 opened about 2 months ago by

Update README.md

#8 opened about 2 months ago by

🚩 Report

#7 opened about 2 months ago by

cannot import name 'NVLM_D' from 'transformers'

#6 opened about 2 months ago by

🚩 Report: Not working

#5 opened about 2 months ago by

License

#4 opened about 2 months ago by

GGUF wen?

#3 opened about 2 months ago by