Should be added sometime early this year. I think it was mentioned in HF blog/article when i was looking for way to use multiple models without restarting llama

Model manager already exist for quite a while, you can load and unload models via webui. I personally uses preset file option. This is new version of the existing mgr

Will he fire himself if he send AI slops?

Wait long long for the imaginary trickle down to happen

We’ll see. More competition the better

How do u know it’s legit?

I didn't. Its docker container running on unraid fwiw.

Probably not helping. All i did was passing /dev/dri as device when i setup my jellyfin container . I

Did you pass the igpu to container?

FWIW, syncthing-fork in F-droid has link to researchxxl's github. The package name still catfriend1 though. https://f-droid.org/en/packages/com.github.catfriend1.syncthingfork/ Trustworthiness is still a question mark though, hence I've not installed in my phone.

Big fat NO

Asia? That salary? Dream on