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.
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.
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 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
Absolutely! And tests are being performed on how to actually make something that is low carbon and practically useful, like in Fjell, in Drammen in Norway. Unfortunately it’s not as easy as finding an aquifer and heat it to boiling point. Here is a link to the Fjell test: https://www.muovitech.com/SE/?page=news&id=649
Well, Yes and no. Water is a great storage, but it is hard to insulate and very corrosive in the long run. And on the grand scale of things, the amount of water that needs to be heated for city scale applications are hard to deal with. There are cities which has connected huge caves to the district heating system, but the amount of energy stored there is rather insufficient. A case in point, Mälarenergi claims that their energy store, the size of about 120 Olympic swimming pools heated to 95 degrees C, would power a city of about 100 000 people for about two weeks in somewhat benign weather conditions.
Winter is longer, though, and we need to find ways of storing more heat for longer to be able to make a real dent in demand. There are other methods though, and even better is that some of them doesn’t need any carbon what so ever to be viable. And with the new EU directives (EED and EPBD) the foundations and Incentives has been given to start the race for better (district) heating solutions.
That’s true. It is also true that power was generated to support the polish market when half of Sweden’s nuclear reactors had to be taken out of production due to some malfunction during a bad cold front in December.
Having said that, electricity is still scarce during winter which means that a lot of it is used for heating. That must end and ideally in a way that let us use the energy excess during summer for heating during winter.
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…
Sorry, didn’t know jokes needed to be geotagged on this instance.
I see the Ukrainian alt army got upgradw on the infantry side.
An LLM once explained to me that it didn’t know, it simulated an answer. I found that descriptive.
That’s optimization for you. Just a 27% increase in size would allow a whole lot of more shapes, but think of the economy!
It would have to be more than that. If it’s supposed to be backed by EU there would have to be an agency responsible for it’s development and security. The moniker “EU certified” would require some sort of code evaluation and certification agency. As such it would become rather powerful.
I think it’s a good idea, the OS would give the market a focus and allow for a collected development effort without excluding anyone active today from participating. Kinda like what I think Android was, without the risk of lock-in as it would be government funded.
The big question is if this would be within the current EU mandate, though.