17
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 23 Jun 2025
17 points (87.0% liked)
LocalLLaMA
2978 readers
58 users here now
Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.
Rules:
Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.
Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.
Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.
Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.
founded 2 years ago
MODERATORS
Mikupad is incredible:
https://github.com/lmg-anon/mikupad
I think my favorite feature is the 'logprobs' mouseover, aka showing the propability of each token that's generated. It's like a built-in thesaurus, a great way to dial in sampling, and you can regenerate from that point.
Once you learn how instruct formatting works (and how it auto inserts tags), it's easy to maintain some basic formatting yourself and question it about the story.
It's also fast. It can handle 128K context without being too laggy.
I'd recommend the llama.cpp server or TabbyAPI as backends (depending on the model and your setup), though you can use whatever you wish.
I'd recommend exui as well, but seeing how exllamav2 is being depreciated, probably not the best idea to use anymore... But another strong recommendation is kobold.cpp (which can use external APIs if you want).