I’m just in the beginning, but my plan is to use it to evaluate policy docs. There is so much context to keep up with, so any way to load more context into the analysis will be helpful. Learning how to add excel information in the analysis will also be a big step forward.

I will have to check out Mistral:) So far Qwen2.5 14B has been the best at providing analysis of my test scenario. But i guess an even higher parameter model will have its advantages.

And exactly why are they missing? Who stole what at Microsoft?

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.

This is expected. Oil prize has been on the decline for some time. I didn’t expect demand to erode this fast, though. which I guess is kinda a good thing.

The only way forward is for renewables to become even cheaper that fossils. Which can be done. The EUs fit-for-55 will bring down energy prizes. Summertime we will see really low electricity prizes the comming decade in Europe because of this.

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 couldnt disagree more with you. If there are pedestrians nearby you drive slow and keep your distance regardless of where you drive.

The same goes for pedestrians, though. Don’t walk where it’s not safe, for everyones safety. Like the interstate. It’s a shared responsibility.

This, however, is in the middle of a neighborhood where a ball and a kid could come flying at moments notice…

You are on to the issue yourself. First and foremost we need to stop releasing CO2. That in and of itself is not enough, but the most important bit. Some countries (a lot?) has enough tree cover to offset a huge chunk of their CO2 emissions today by trees. Some might even be CO2 neutral, had it not been for the use of wood for fuel. Therein lies the potential. And this is already a mature industry with market dependencies well established.

Resembling this CO2 uptake with man made processes will require a monumental investment in both monetary and energy terms and the output will be pitiful when the net effect is calculated.

So slamming the effect of trees, which does not require any of that development and investment costs because it doesn’t solve the entire problem, because it isn’t a silver bullet is rather short sighted. It is already today the best tool we have to sequester carbon from the atmosphere for cheap and with a comoditiezed biproduct.

What’s wrong with trees? They cost next to nothing and runs on renewable energy.

For me it’s the opposite. My body may be on the premises, but mentally…

Well, that’s been the basis for some other products. AMD and Intel comes to mind😊 They both have IP the other need and historically Intel has been the dominant one, but now the tables have turned somewhat.

I’m itching for a shovel, though…

Oh, welcome to the eu. Speed limits are going down, generally. At least in this nick of the woods, we aren’t driving as fast as in the eighties. The goal is zero Trafic fatalities.

I feel that is the issue with this post to begin with. Is it a shitpost or not? Seems more like a load of hot air to me

Is that a second generation immigrant, married to a first generation immigrant, stealing pets in Ohio?

Anything that is more about talking to different parties rather than documenting and being the one to deliver. the more specialised people the better you connect, the bwtter. They will love your ability to see the patterns of the work place, your helicopter perspective. That will help them to test their ideas, to understand the concepts and what their task is all about. They will also love that you will not micro manage (as long as you dont end up hyperfocusing on their topic) and let them do their thing.

Don’t be the specialist. Don’t be the one that tries to have an eye on all the details, all the numbers. I tried to be an accountant for a while…

slow clap