HateLLM will be a smash. /s

I use this: https://cloudhiker.net/explore

If at all true this would be world-changing news.

Lovely! I'll go read the code as soon as I have some coffee.

I'm sorry but how is that possible? I'm here and I have eaten fish all my life, 50 years of it.
Had bloodwork done a few weeks ago that included count for heavy metals.
No sign of any kind poisoning.
The whole country should have from mild to heavy poisoning by now... And yet they don't.

How do you explain this discrepancy?
How much mercury did your friend had before coming here? How much was it acquired here?
Fish of all kinds is a staple of mediterranean common diet, there should be people dropping left and right...

Goddammit! Don't tell that one, I use it to impress random people at parties.

[Shift] + ZQ

Messing around with system python/pip and newly installed versions till all was broken and then looking at documentation.
This was way back on the 00's and I'm still ashamed on how fast completely I messed it up.

Me with four open cli terminals righ now:
https://i.kym-cdn.com/...

Just pip install mscandy -U

Just deleted my accounts a few moments ago.
I was there since Digg.

I got cancelled too and chose Hetzner instead. Will not do business with a company that can't get their filters working decently.

Got one more for you: https://gossip.ink/
I use it via a docker/podman container I've made for it: https://hub.docker.com/...

Oh my Gwyn, this comment section is just amazing.

I don't think people realize how much data they leak daily.

Not close enough for V.A.T.S.

I do SDXL generation in 4GB at extreme expense of speed, by using a number of memory optimizations.
I've done this kind of stuff since SD 1.4, for the fun of it. I like to see how low I can push vram use.

SDXL takes around 3 to 4 minutes per generation including refiner but it works within constraints.
Graphics cards used are hilariously bad for the task, a 1050ti with 4GB and a 1060 with 3GB vram.

Have an implementation running on the 3GB card, inside a podman container, with no ram offloading, 1 vcpu and 4GB ram.
Graphical UI (streamlit) run on a laptop outside of server to save resources.

Working on a example implementation of SDXL as we speak and also working on SDXL generation on mobile.
That is the reason I've looked into this news, SSD-1B might be a good candidate for my dumb experiments.

That's wonderful to know! Thank you again.
I'll follow your instructions, this implementation is exactly what I was looking for.

Just figured out there are 10 places called Lisbon dotted around the US, according to the search.

While designing a similar classifier, I've considered the idea of giving it the whole thread as "context" of sorts.
Not just the parent comment, the whole thread up to original post.

I've abandoned the idea.
A comment must stand on it's own, and it would put limits on results, the way I was planning to do it.
I might be very wrong, your insight into this would be very helpful.

My original idea was to go recursively trough the thread and test each comment individually.
Then I would influence the actual comment results with the combined results of it's parents.
No context during inference, just one comment at a time.

For example consider thread OP->C1->C2->C3.
My current model takes milliseconds per test with little resources used.
It would be ok up to very large threads but would contain a limit to save on answer time.
I want to determine if Comment 3 is toxic in the context of C2, C1, and OP.
Test C3, test C2, test C1, test OP. Save results.
My current model gives answer in several fields ("toxic", "severe toxic", "obscene", "threat", "insult", and "identity hate")
The idea was to then combine the results of each into a final result for C3.

How to combine? Haven't figure it out but it would be results manipulation instead of inference/context, etc.

Edit: Is there any way you can point me at examples difficult to classify? It would be a nice real world test to my stuff.
Current iteration of model is very new and has not been tested in the wild.