Oh hey, it's you again. I hope your blog continues on for some time to come
The reason to host your own instances is altruism. You help out the community with decentralisation and also absorb some of the bandwidth and storage costs from other instances. This is necessary for the Fediverse to survive.
Thanks man, that would be much appreciated
Thanks, looking forward to it
You got an RSS feed for me?
Ban was unjustified. db0 needs to at least point to someone accountable, seeing that he is still the benevolent dictator
Send the link to the discussion and the screenshot of your comment
Thanks for the edit. You have a very intriguing idea; a second LLM in the background with a summary of the conversation + static context might make performance a lot better. I don't know if anyone has implemented it/knows how one can DIY it with Kobold/Ollama. I think it is an amazing idea for code assistants too if you're doing a long coding session.
I see. Thanks for the note. I think beyond 48GB of VRAM diminishing returns set in very quickly so I'll likely stick to that limit. I wouldn't want to use models hosted in the cloud so that's out of the question.
I didn't think of that. Indeed, DNS caching/using different DNS servers for different devices will break it exactly like what OP is experiencing. Thanks.
Yes, but DMZ is a better solution if you want to let Router 2 handle your network