Open tgaddair opened 8 months ago
If I may add some suggestion, please take care to make HUGGING_FACE_HUB_TOKEN variable optional, because even if I intend to serve local model only, LoRAX demands this variable ... Btw I use the model that is on HF gated repo.
Download process here will be essentially a no-op if the model weights are already present, but this can add several seconds of latency to startup.
We can make a quick check from within the
lorax-launcher
to see if the model weights exist and if so, skip this call entirely.