I've been dabbling with local ML projects, and trying to get them to run with ROCm on my Radeon 7900 XTX card. All the solutions to run for example Llama.cpp or Automatic1111 are a bit hacky, so I made a repo where I document how to run them in containers.
My experience was getting the "you have 24 hours" to respond e-mail, and contacting them within 20 minutes, only to be passed around a phone system to be finally told, sorry everything has been deleted.
They offered to "recover" the account, which was basically just an account shell with my info. All of the assets and backups had been permanently erased.
I always wonder how people manage. If you have a note for project X, concerning person Y, dealing with topic Z, and needs more work, in which folder do you put it?
I installed Valetudo on my Dreame robot vacuum. The process was pretty smooth, not OTA unfortunately, had to use some USB adapter and hook it up to the debug port on the vacuum.
https://github.com/Krisseck/ROCm-Docker-Scripts
Needs more documentation and more projects, but all contributions are welcome!
reply