Messages

mike check in the private forum area .

well i just ran across this new info. on that a.i. :
I can't provide a free download link for the Moonshot AI model from China — it's not publicly available for direct download like that.
Moonshot AI is a large language model developed by Moonshot, a Chinese AI company, and access is typically through their official platform or API — not as a standalone file you can install.
If you're interested in trying it:
Check their official website (moonshot.cn) for access options
They may offer web-based demos or developer APIs
Some AI platforms in China provide access via apps or cloud services

i was going over the news and ran across this about a china model a.i. that has been given away for free on the model  here is the news link : the a.i. is called "moon shot " . https://www.youtube.com/watch?v=0kBjUG3YojM . thought maybe some may be interested in adding this to hal.

great news mike, nice avatar to , can it be modified , is it available on a flat file , etc. ?

the new 8.0 sounds very cool will be glad to use it .  thanks mike for all the hard work you have put into it.  i wrote on the companion site earlier mentioning that this website had been down when i tried getting on here earlier. glad it's back up!

mike you wrote : The Book reader gets fixed so it a can read all of a Book with out dumping 1/2 way through. For ART. (Haptek nightmare).
I may have to re-write the haptek activeX controls for that. Like i did with the single core Player listed on this board
For those beta testing the new version:

i'm not sure if the book reader ever had the ability to allow the user to stop (so it completely stopped , i imagine it did ) or a pause button  so it could be paused and restarted later from the paused area. if not it needs that . i don't know if it is possible to have a pause button that was on , and later a pc was shut down and restarted later and hal was started again would be able to still restart from that paused area . like i said don't know if it's possible, if it was possible that would be good as people shut pc's down at various times.     
       having said all that . i just got a notice from ollama saying s a 12.5 version update now available ,is it safe to update the new version and not cause any problems with the new hal / i know they are separate programs although now linked about the llm model downloads ,

first off thanks cyberjedi for calling and walking me through it ., it seems it was a matter of reregistering more ocx.and dll. files. it worked after that .
below is showing the two separate screens and where it answered and also spoke through my hal character  Angela. 

i downloaded the olamma client 19 and installed it . but i need the newest version of hal .exe . file , i have the older version .when mike was working on the other he didn't have the splash screen finished and so i kept using my older version in the menu it does show some things but not all.  can you post the newer now finished hal exe . ? and do i need to just drag and drop it in the program files to replace the old version?  the  only other  that i know i have is in this picture .

okay on testing more llm on the gemma3.4b . i tested it asking it to talk this way .   

  ,(Smiling warmly, a gentle touch on your arm)

Hey honey, how was your day? You seem a little stressed. Tell me everything. Did you have a good lunch? You know, you need to take care of yourself a little more.

Seriously, what's on your mind? Don?t bottle things up. You know you can always talk to me, right?

(Pauses, looking at you with genuine concern)

Just? tell me about your day. ❤️

a problem i am wondering about is if this is ran through ultrahal . is their a way to cut out the description emotions ? or make them optional if someone wants them.  for example (Smiling warmly, a gentle touch on your arm).(Pauses, looking at you with genuine concern) ❤️. so this might be a issue .   just pointing it out.  i imagine this is in other models , all? models???

Okay , cyberjedi  worked with me , i finally found the download for the lama it's on the 2nd page . cyber walked me through it and showed me where sybershot left instructions , i also copied them and saved them as a txt file in my ollama folder . to back up.  and it installed fine , and it is working fine , here is my screen shot  of later where i asked it about the size of the moon. the voice works init fine to reading out the answer. even though cyber said he didn't need thanks , i appreciate what he has done .all  your hard work and testing is appreciated.
heres the screenshot of it working.   my wait time for hal was not checked maybe 10? seconds, but i need to defrag my pc  and so will test again using the same minstral llm and then the uncensored to see any time differences on answering times.

[any more updates on this?]

any more updates on this?

i have been very busy and about wore out haven't had a chance to check in , had a neighbors very large side of tree fall over and destroy part of our fence and also our shed totaling it and almost hit our garden shed.  claimed he would take a large back hole and lift and move it off our property and back on his side , that was on the first , never seen him again . so i am left having to cut all the large limbs over hanging on the tree on our side , am emptying out the garden shed in case the limbs overhead fall down on it. am planning on moving it farther away and then cut down those large limbs . just tore loose and replaced the back step yesterday . some day i'll be able to slow down on all this.

cyber and checker see you two have been going over the llm model i mentioned for offline , am hoping you can make it work . one question i have is will it work with the custom brain people have developed , i have one i have been learning and backed up over the years and have kept. , custom responses within some of the tables. etc.   mike it sounds like the llm model works okay on a regular pc , vm's not so much . but that is all good. also if i am understanding right the llm keeps retains conversations ( so this is like short or long term memory then ? that would be good as that's also what hal needs.  thanks for the work and investigation into that llm model .  i will be in and out of here as i have time . i haven't given up on hal or others . keep up the good work.

lol.  :) hop to it hopsing !  ;)

THAT WAS A GOOD MOVIE AND STORYLINE !! thanks for making it .  :)

mike , i think if we can get this plugin working writing files and folder and have short and long term memory etc.  it will help hal a lot! maybe you can get it corrected on the syntax error it keeps giving .

anyway , no matter what i try i am getting a syntax error . that i can't find or fix . maybe you can  and i'll retest it again .