I have experience in running servers, but I would like to know if it’s possible to do it, I just need a GPT 3.5 like private LLM running.
It’s doable. Stick to the 7b models and it should work for the most part, but don’t expect anything remotely approaching what might be called reasonable performance. It’s going to be slow. But it can work.
To get a somewhat usable experience you kinda need an Nvidia graphics card or an AI accelerator.
Intel Arc also works surprisingly fine and consistently for ML if you use llama.cpp for LLMs or Automatic for stable diffusion, it’s definitely much closer to Nvidia in terms of usability than it is to AMD
I need it to make academic works pass the anti-AI systems, what do you recommend for that work? It’s for business so I need a reasonable good performance but nothing extravagant…
I believe commercial LLMs have some kind of watermark when you apply AI for grammar and fixing in general, so I just need an AI to make these works undetectable with a private LLM.
I believe commercial LLMs have some kind of watermark when you apply AI for grammar and fixing in general, so I just need an AI to make these works undetectable with a private LLM.
That’s not how it works, sorry.
I was talking about that with a friend some days ago, and they made an experiment, they just made the AI correct punctuation errors of a text document, no words at all which you can easily add manually, and the anti-AI system target 99% AI made, I don’t know how to explain that, maybe the text was AI generated also IDK or there is a watermark in some place, a pattern or something.
Edit: you point will be that there is no way to fool the anti-AI systems running a private LLM?
My friend used to employ several people for that, but they started using AI to work less so he decided to start doing by his own with AI instead of paying someone else to do the same.
They’re Ryzen processors with “AI” accelerators, so an LLM can definitely run on hardware on one of those. Other options are available, like lower powered ARM chipsets (RK3588-based boards) with accelerators that might have half the performance but are far cheaper to run, should be enough for a basic LLM.
Look into ollama. It shouldn’t be an issue if you stick to 7b parameter models
Yeah, I did see something related to what you mentioned and I was quite interested. What about quantized models?
Quantized with more parameters is generally better than floating point with fewer parameters. If you can squeeze a 14b parameter model down to a 4-bit int quantization it’ll still generally outperform a 16-bit Floating Point 7b parameter equivalent.