New on LowEndTalk? Please Register and read our Community Rules.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
[2024 EXTENDED] Black Friday / Cyber Monday: FLASH SALE & MEGATHREAD
This discussion has been closed.
Comments
Yes sir!
Great deal then!
@raza19 will still miss it, coz hes driving!
Glad that worked. So what this box gonna serve?
@raza19 c'mon get in here
Clever code! Got one!
Monitoring my nodes in DE, nothing fancy.
When buying an idler and you don't know what to do with it, just make it monitor the other idlers. Very smart.
One of my takeaways from this year’s BF deals
vps with extraordinary performance from @kuroit
@seenu can vouch for his Windows RDP performance for @kuroit VPS with just 4gb memory.
That's how you deal with the bots. Take notice @gigahost @host_c
Did anyone try the "Experimental 1206" model in AI Studio?
It's said to be very good for coding and you can use it for free
https://aistudio.google.com/
Meta has one too it seems but first time i hear about these
I got it I got it. I canttttt fking believe but I got it
after a thousand pages 😭😭😭 I got it 😂😂😂😂😂😂😂😂😂😂 U great human being @kuroit. May U live long and prosper. @emgh I got it @FAT32 I got it. Listen world I got it 
luving the control panel though 
:D:D
But i have tried gemini but is shit and wont help with real useful stuff because of censorship
lmao
congrats
I thought you missed it
Experimental 1206?
No the one that can be found in google console, that you can install in vscode as well.
Wait is there something wrong with using vscode
any recommendations for selfhosted llm which would help with code generation? Claude does amazingly well, but I end up making it work so much that I am rate-limited.
Have you tried wizardcoder?
llama.cpp is a lightweight C++ framework designed to efficiently run LLaMA models (and derivatives like WizardCoder) on local hardware, including CPUs, making it an excellent choice for self-hosting on a VPS. It provides highly optimized implementations that support quantization, allowing large models to run on modest hardware.
VPS with 4x vCore / 8 GB memory can be used to self host Llama.cpp
I just started thinking of selfhosting llms. will definitely try this.
Any recommendations for a UI to slap in front of this and other llms?
Thanks
Yes there is but I haven't really used it so I don't know
Tldr; he got it
I have updated that post with more details
https://lowendtalk.com/discussion/comment/4172297/#Comment_4172297
and is happy*
got it. thanks
@plumberg
https://github.com/ggerganov/llama.cpp