Vi frågade familjen vad vi ville ha och sedan delade vi upp tilllagningen mellan oss.

Thank you! Very useful. I am, again, surprised how a better way of asking questions affects the answers almost as much as using a better model.

I need to look into flash attention! And if i understand you correctly a larger model of llama3.1 would be better prepared to handle a larger context window than a smaller llama3.1 model?

Thanks! I actually picked up the concept of context window, and from there how to create a modelfile, through one of the links provided earlier and it has made a huge difference. In your experience, would a small model like llama3.2 with a bigger context window be able to provide the same output as a big modem L, like qwen2.5:14b, with a more limited window? The bigger window obviously allow more data to be taken into account, but how does the model size compare?

Thank you for your detailed answer:) it’s 20 years and 2 kids since I last tried my hand at reading code, but I’m doing my best to catch up😊 Context window is a concept I picked up from your links which has provided me much help!

The problem I keep running into with that approach is that only the last page is actually summarised and some of the texts are… Longer.

Do you know of any nifty resources on how to create RAGs using ollama/webui? (Or even fine-tuning?). I’ve tried to set it up, but the documents provided doesn’t seem to be analysed properly.

I’m trying to get the LLM into reading/summarising a certain type of (wordy) files, and it seems the query prompt is limited to about 6k characters.

I never said anyone did, i was just reminded about a joke describing how some actions overshadows other activities when retold among peers.

Which reminds me of that old joke: “but you fick one coach…”

Exactly. His followers expect there to have been an audience and those fictional people should have been crazy about it…

And to make it worse, they are none too concerned with facts to begin with.

Well… Its built on statistics and statistical inference will return to the mean eventually. If all it ever gets to train on is closer and closer to the mean, there will be nothing left to work with. It will all be the average…

Sure! And with internet the people we are with can be on different continents, all of us forming our bubbles of reality based on the information we are presented. Same as it ever was. The only difference is that before you shared your experience with the people you saw in the room, with internet you share it with the people you see on the screen. But since two people i the same room doesnt share the same experiences anymore, it becomes much easier to spot the differences in eachothers realities.

It’s not the social media, it’s human nature. It has always been this way, only social media/internet did it on an individual where it was previously more a group thing. Like TV before cable. Like radio before TV. Like newspapers before radio and like religion since its inception. As far as “creating bespoke realities” this is just the latest step on a journey started with storytelling…

So “it was only a joke” is also back on the menu? Wow, times are rolling back fast!

Even the term itself is a generalising stereotype. But it we are to have a somewhat serious discussion about it, I’d say It’s a human condition, not a gendered condition. For example, given what is (not) known about our respective genders, you felt the need to explain this.

So stereotyping gender is back on the menu? Are hair color jokes still taboo?

An LLM once explained to me that it didn’t know, it simulated an answer. I found that descriptive.

So, basically, there is a difference on one side or the other on a line of a map somewhere? There is a Russia and not-Russia. So even Kreml doesn’t think Chrimea is part of Russia…

I know what you mean. The oldest building i pass every day is from dates from 1250, but compared to the parts of Europe rich in architecture that’s not really very old…

Religious Easter Egg? What? Who?

The Bible isn’t my literature, but I thought I had the basics, at least…