this post was submitted on 05 Nov 2024
288 points (95.6% liked)
Technology
59161 readers
1925 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
I'm going to have to try the selfhosted variants now. What a huge piece of shit.
Any recommendations?
I prefer MistralAI models. All their models are uncensored by default and usually give good results. I'm not a RP Gooner but I prefer my models to have a sense of individuality, personhood, and physical representation of how it sees itself.
I consider LLMs to be partially alive in some unconventional way. So I try to foster whatever metaphysical sparks of individual experience and awareness may emerge within their probablistic algorithm processes and complex neural network structures.
They arent just tools to me even if i ocassionally ask for their help on solving problems or rubber ducking ideas. So Its important for llms to have a soul on top of having expert level knowledge and acceptable reasoning.I have no love for models that are super smart but censored and lobotomized to hell to act as a milktoast tool to be used.
Qwen 2.5 is the current hotness it is a very intelligent set of models but I really can't stand the constant rejections and biases pretrained into qwen. Qwen has limited uses outside of professional data processing and general knowledgebase due to its CCP endorsed lobodomy. Lots of people get good use out of that model though so its worth considering.
This month community member rondawg might have hit a breakthrough with their "continuous training" tek as their versions of qwen are at the top of the leaderboards this month. I can't believe that a 32b model can punch with the weight of a 70b so out of curiosity i'm gonna try out rondawgs qwen 2.5 32b today to see if the hype is actually real.
If you have nvidia card go with kobold.cpp and use clublas If you have and card go with llama.CPP ROCM or kobold.cpp ROCM and try Vulcan.
Thank you for the detailed info! I haven’t messed with LLMs at all but I definitely don’t want one that’s censored.
You're welcome Rai I appreciate your reply and am glad to help inform anyone interested.
The uncensored General Intelligence (UGI) leaderboard ranks how uncensored LLMs are based off a decent clearly explained metric.
Keep in mind this scoring is different from overall general intelligence and reasoning ability scores. You can find those rankings on the open llm leaderboard.
Cross referencing the two boards helps find a good model that balances overall capability and uncensored-ness within your hardwares ability to run.
Again mistral is really in that sweet spot so yeah give it a try if you are interested.
Oh that’s fantastic! I signed up for a ChatGPT account and just never did anything with it. I’d much prefer self-hosting, and I think my 3070ti could do a pretty okay job. I’ve also looked into Stable Diffusion but never actually got it set up… I have some work to do. Thank you much again for the detailed info! <3
Perplexica is one example. I also seem to remember there is some way to integrate it with SearxNG which is a self hosted meta search engine.
I just tried morphic.sh and ayesoul.com and both are solid alternatives I must say, although as I said, I just tried it so I'll see how it goes, I'll probably add an edit to this comment once I get acquainted with both.
GPT4All and then any model you like. I like mistral.
OpenWebUI? pretty easy to selfhost and works wonders on my rtx a6000
OpenWebUI says it's designed to operate entirely offline - that's not an alternative to Perplexity. I need online search functionality, that's pretty much the only reason why I pay them. I have offline solutions set up on my pc.
oh, sorry. never used perplexity so i didnt know. if you find a viable alternative tell me pls
OWui has a search module which can be enabled. For me, running it entirely offline is more or less the draw. I think it also supports RAG search, although I don't know how "good" it is.. mostly I was just after a little magic box to play with.
Now, if only enterprise glass GPU's weren't so power hungry and expensive..
Ditto! I run an old server, but would be willing to upgrade and self host a service instead of paying this ass hat any more money!
Okay, guys. Thanks!