Aaron Pham

I can't seem to run inference on M1 for starcoder and falcon

Got it, will look after I finish the fine-tuning API

Will track on the development of #178

I think this is very low, we can do it later

Hey there, how much memory do you have available? Often time this error is raised when there is OOM issue.

Hey, can you try out with 0.1.14?

Please reopen if you still run into this issue

Yes, I'm currently working on fine tuning API atm

Peft and LoRA is now supported during serving and building time via `--adapter-id` I will continue to gradually add support for all default fine-tuning layers for each of the models....

This is strange. Did you run into any issue when running containerize?