dupa

Recent Posts

Pages: 1 ... 6 7 [8] 9 10
71
CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?
« Last post by sybershot on September 23, 2025, 02:53:40 pm »
Just tested ollamaclient18.exe with model selection, and tried model Dolphin3 it worked beautifully as expected 2x thumbs up. I had it tell me a joke and response speed was about 1.1 second
72
CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?
« Last post by lightspeed on September 21, 2025, 04:11:48 pm »
any more updates on this?
73
CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?
« Last post by Checker57 on September 21, 2025, 12:29:28 am »
Cyber!?  Really?!  Epic, you wizard!  I've got to spend a few cycles and check it out this weekend.  I knew you could do it with the passion you have for great thinking! 

We're definitely on a better path to smarting up HAL with the new tech available.  Obviously, I still prefer to have HAL base its conversations and "culture" on the one we train it to have, rather than a culture "off the wild web".  But, great progress!!!  Bravo!

You have surprised Atera that she may be drilling for gold in AI land soon enough.  ;-)

Checker57
74
CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?
« Last post by cyberjedi on September 20, 2025, 07:25:32 am »
Hey hey Guys:
hey Sybershot check this out homie
The new upgrades are in progress
Still neeeds more work, but oh boy
75
CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?
« Last post by sybershot on September 19, 2025, 10:51:41 am »
tested and works 100% with a 1.1  second response time on my main rig. specs= (mobo= z890 AI top,  cpu=ultra 9 285k,  ram = 64gb ddr5,gpu=  5071ti 16gb vram, drive= 4tb nvme)

great job brother  ;D Welcome to the future  ;)
76
Congratulations brother, that's defiantly a huge milestone there  ;D
Hal learning from Mistral or any other llm indeed will keep Hal at the number 1 spot for years.

I still need to figure out this rich text field phenomenon, I m going to have to try it on Windows 8 
77
CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?
« Last post by cyberjedi on September 17, 2025, 07:04:45 am »
hey hey guys/gals (Update: as of this posting the json errors have been fixed and it talks using sapi5)
Wouldnt mind some input from Robert, any suggestions.What you like to see happen .
checker57 you likey?????

hehehehe sybershot

You see where this is going now
Next is cutting this into hals code so they can talk....BOOM
Hal gets smarter as he engages, OH OK up to NOW Hal has had no equal. Once hals brain swells to 1 gig, drop that in as a stock ultrahal and compare the 2, thers no name involved so we shouldn't have a conflict in that regard.
You might get this to work on Linux Dist'ls (with WINE of course)
Once you start Mistral, This will hook it, or what ever you have installed, its currently set to mistral, but you do have options to down load a choice of LLm's
Working on the code to start ollama from the gui it self
This will undoubtedly run faster when not on what is running with this machine
This is kinda awesome in the sense that the long time frames aid in Ultrahal having the time needed to write the SQL itself, i had this issue years ago.
Any one that wants to play with me hit me up

VB still just ROCKS, when its all gotta get done. Get ready for the greatest A.I as it flexs up yet AGAIN. But this time targeting the database it self
sqlite has a max of 2TB, hal is  rocking 120 megs out of the gate. Mistral is NOT a big ass wiki..... and yet it is in there as well.

https://ollama.com/download/windows
Install ollama mistral 7B (Mistral-7B-Instruct-v0.3)
Keep in mind i could just as easy to turn that into the next ULTRAHAL add haptek, chant engine,few other dudads and presto... I want to preserve ultrahal
But there may be special editions for people on the cool list.
Does NOT like win11

Remember this is just half, The other half is getting them to talk to each other, but it starts here
While you cant directly edit the LLM, you can back door it by appending new datasets to it, one way is SqLite. which ive started the code base.
3rd Option is to let Hal run the LLM as a stand alone pure LLM Hal.


Cyber Jedi
78
CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?
« Last post by sybershot on September 05, 2025, 05:59:12 pm »
I have not played with the regular Mistral models, I however been using Codestral 22b lately
79
CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?
« Last post by cyberjedi on September 03, 2025, 09:28:40 pm »
Hey hey guys:
Im basing what im saying on another construct robert did 13 years ago.
The only issue was Robert had nothing to run against hal, nothing was smart enough, SHOCKER,,, loll
The game has changed now.
As you can see, what ur suggesting is just not happening here. So we will see.
https://www.youtube.com/watch?v=X_tvm6Eoa3g
We may want to try a blank slate brain as well, the possibility's are endless with Hals learning set to max
Im talking about this kinda thing running 24/7 non stop
gotta get it working first lolol
Its gotta work on this machine, if so, chances are great it will work on any machine then.

cyber

Update: Mistral is the new hands down winner, speed,no thinking text. Answers are awesome. spechs: 08 core machine, with vm running win 10 + ollama.
answers are leading as well, thats a biggy, download and instal Mistral...
So, Mistral 7b seems to be what were after for a teaching model. SO far
performance is 300%
https://ai.invideo.io/watch/Gd18vs6nocT

80
CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?
« Last post by sybershot on September 02, 2025, 04:12:11 pm »
I believe I see where Checker57 is coming from [If taught by a large wiki, Hal will sound like a large wiki]
Hmmmm I wonder:
Will Hal succumb to bombarding the user with the Wiki's(llm) believed facts with almost every reply?
Ollama and many others are trained on certain viewpoints that may or may not be true.
Will our Hal to try and persuade us of false or misguided narratives?
I love the Idea, so please don't take it wrong way, I'm not attacking the idea, I'm just giving some food for thought during your journey  ;)
Pages: 1 ... 6 7 [8] 9 10