CodeCoffe

I believe it is still a valid enhancement request. I am aware that I could try building my own platform and use textgen webui only as inference, but I'd love...

> I am perfectly able to run several instances using docker, so that is something you can try too. But wouldn't that result in multiple instance being loaded at the...

``` Distributor ID: Ubuntu Description: Ubuntu 22.04.3 LTS Release: 22.04 Codename: jammy sadmin@aiml:~$ uname -r 5.15.0-89-generic ``` ollama serve and ollama webui. But the process spinning the CPU and GPU...

I de- and reactivated conda, tried installing packages, all up to-date, issue is the same in this environment. I am just recreating a new env and installing it on another...

That would be strange, as usually after a single OOM exception I need to restart the entire script to make it work again, but in this case it starts working...

I wasn't able to recreate this and since that, reinstalled my machine. I believe it probably would have been solved with a reboot or reinstall of dependencies. I'll close it...

I would love to see this. if I have the time, I will try to put it together and commit for review.

I have the same issue, but in my case the script isn't working either: ``` python3 convert.py models/alpaca-7B-ggml/ models/tokenizer.model: [...] raise Exception('Invalid file magic. Must be an old style ggml...

So basically ``` function gracefull_exit () { apply_Dell_fan_control_profile enable_third_party_PCIe_card_Dell_default_cooling_response echo "/!\ WARNING /!\ Container stopped, Dell default dynamic fan control profile applied for safety." exit 0 } ``` | |...

Facing exactly this. It just gets stuck after "being done". ``` Preparing transaction: done Verifying transaction: done Executing transaction: done # # To activate this environment, use # # $...