Shaun

Thank you for your response. What would be your suggestion to host the model locally within company cloud infrastructure to avoid repeated downloads from hf for model/pipeline initialization ?

Thank you

nvidia smi - """+---------------------------------------------------------------------------------------+ | NVIDIA-SMI 535.161.07 Driver Version: 535.161.07 CUDA Version: 12.2 | |-----------------------------------------+----------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp...