lamma.cpp is faster than olama + ollama is build on top of lamma.cpp so its a wrapper for lamma.cpp
lamma.cpp is the way even for beginners. You can easily use hugging face models ( just download an use them) and if you use ollama and downloaded...
I don't know, if I should be able of that. But since I'm not I find it better to review than wild unconsidered typing.
And looking at many other posts I doubt everybody else but me is capable of getting everything right in the first take, even if...
Nope. You can run commercial software on the linuxulator. However, the install program, and / or the startup scripts might not work unmodified on FreeBSD with the linuxulator.
Also, if the program in question requires one or more shared (linux)...
FWIW, the lama_run.sh (my name) script fails if the models are stored in a directory tree with depth > 1.
Example:
tingo@locaal:~ $ find $HOME/.cache//huggingface/hub -name "*.gguf"...
You are probably using a newer version of llam-server than me, mine does not ssuport lod-mode,. it seems
tingo@locaal:~ $ sh bin/run_llama.sh
Pick an AI model to run:
1) 0.00G Qwen3.8-27B-IQ2_XS.gguf
2) 0.00G...
A solution that surrounds everything? I play mostly classic DOS and PS1/PS2 games and some Nintendo from a local medium. Steam games could be an additional option. Games are all fullscreen, so the technical difference doesn't have to exist. A...
Oh there are a ton of benefits for programming with AI, as a tool for programmers.
In hands of non programmers it is a slop machine. You simply do not have enough knowledge to force it on track with right decisions. You cannot have enough...
Asking people to choose case for a steam machine
that doesnt have any code yet is jumping the gun a bit.
our SteamBsd machine,
you mean my SteamBSD machine
apart from you
i dont think anyone else would want to use vibe coded Freebsd steam...
A portal for ALL games would be more interesting. While I never used it, how is Steam not just a remote fileserver + closed source graphics driver? I don't think there's a real service. It's based on a unfair technical advantage of having the...
Hmm, is there a quicker way of finding out if a given model fits into your GFX card memory than downloading and trying?
tingo@locaal:~ $ llama-server \
--host `hostname`.local \
--port 8081 \
--ctx-size $((64 * 1024)) \...
Has anyone tried FreeCORE yet? I was actually working on porting TrueNAS from GitHub myself! I got a successful build, though I was still sorting out some Samba issues. I was checking to see if I could legally release it when I realized someone...
So went back to quarterly and now this shows as i would expect:
# pkg upgrade
Updating FreeBSD-ports repository catalogue...
FreeBSD-ports repository is up to date.
Updating FreeBSD-ports-kmods repository catalogue...
FreeBSD-ports-kmods...
Aye. It's a tumultuous time. Love to look up the history of the area where some of my ancestors came from too. To get an idea of the world view they might have had.
Haven't found any nobility, nothing like that. Some interesting jobs but mostly...
aha!
it's not an error, the machine is named locaal.local.
So a bit of change
tingo@locaal:~ $ llama-server \
--host `hostname`.local \
--port 8081 \
--ctx-size $((64 * 1024)) \
--temp 0.6 \
--top-p 0.95 \...
Having recently traced my family history going back 300 years, I would like to create something to hold my family tree.
Searching around for tools I came across https://www.grampsweb.org/ but am not sure how this works, and wondered if there is...
Right, considering the options, we are simply going to serve a static single-page website (see image) when a DDoS occurs, and switch back to normal operations when it's over. The Anubis solution has been partially successful, but it still adds...
We're back to the pre-Anubis setup. Especially Safari users were negatively impacted, possibly due to the hurried Anubis setup and some related errors in its logging (a not entirely functional ip:port combination in X-Forwarding headers and...
Update: the DDoS has passed, but this line of defense will stay in place for the time being. We can switch back and forth between the two setups (with and without Anubis) and will probably make that happen in the near future.
Webbased: www/webtrees22
Works really well. Also allows you to create various events (birth, baptism, marriage, death, etc). You can also store your references, pictures and whatever else you may have found. I used it for my family tree (I'm...
there is a bunch of genealogy software that is free, here is an article https://www.linuxlinks.com/familyhistory/
some of these are web based.
The important thing is to choose one that can import and export in GEDCOM format (common to genealogy...
I have used Gramps on Freebsd before its really good
Gramps is a gui application,
no need for apache
sudo pkg install gramps
gramps-6.0.8 GTK3-based genealogy program
My ancestors in Wales
Also, xorg-server doesn't even have a dependency on the nvidia-drivers. Even if -nox11 would have accidentally ended up including X, it still doesn't explain the NVidia drivers. Also interesting, it wants to install nvidia-driver-340 and...
there is a bunch of genealogy software that is free, here is an article https://www.linuxlinks.com/familyhistory/
some of these are web based.
The important thing is to choose one that can import and export in GEDCOM format (common to genealogy...
Just to clear one thing up: these weren't AI/LLM crawlers, or crawlers per se.
These were bots requesting the front page (GET /) and immediately closing the connection to do it again and again and again.
This was done by several thousand IP...
Wanting to run pkg upgrade i noticed that some packages wanted to install a lot of additional pkg such as xorg-server, nvidia drivers and so forth some of these packages like wireshark-nox11 you would expect wouldn't need this at all !?
# pkg...
Having recently traced my family history going back 300 years, I would like to create something to hold my family tree.
Searching around for tools I came across https://www.grampsweb.org/ but am not sure how this works, and wondered if there is...
This is a continuation on my local LLM thread, which is hard to reply to. This one might be easier.
https://forums.freebsd.org/threads/running-a-gpu-accelerated-llm-on-freebsd-2-line-howto.102445/
I wanted to waffle a bit more about the...
Maybe someone testing their botnet to see how well it performs in a live DDOS attack against a real target. Depending on the results, would allow them to refine their attack system, before they go on to attack other real targets. As you say...
I think the admins/moderators of this forum aren't properly appreciated. They are VOLUNTEERS. They invest their own time to make sure this forum functions.
DutchDaemon is always looking after the technical aspects of the thing.
SirDice answers A...
Its a vibe code idea/project that people nowadays do all the time.
Nobody ever cares about maintenance. The fact that zioMario is going to orchestrate a bot to produce millions lines of code nobody understands is totally irrelevant.
Nobody can...
Your asking other people to figure out everything for you
If the Freebsd devs could fix the issues with the linuxulator then they would have
there would be posts on the mailing list saying we are working on cgroups or namespace
Thats the whole...
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.