happyborg, to llm
@happyborg@fosstodon.org avatar

Other than (maybe) describing images, what has anyone found #Llama #LLM useful for?

I'm trying it occasionally on different things but mostly it isn't up to the task. For those simpler questions it can answer it is way slower than doing a web search. 🤷‍♂️

happyborg,
@happyborg@fosstodon.org avatar

@jsbarretto that's not something I have much use for, but I'm also wondering if they (though I was really taking about #Llama) produce plausible summaries or good summaries.

happyborg, to llm
@happyborg@fosstodon.org avatar

Having forgotten everything I ever knew about #Perl I'm trying to extend a script I wrote years ago and am almost at the point of asking #Llama #LLM for help.

I mean, assigning a string with an embedded variable really should not be hard 🤷‍♂️

All in an effort to make my faithful old #ftpdns use SSH and SCP instead of FTP, which stops working every time someone in a datacentre sucks their teeth.

If it works I'll have to rename it DIY #DNS.

kjr, (edited ) to llm
@kjr@babka.social avatar

Really amazing... and a good help, thanks @mozilla

Mozilla Lets Folks Turn AI LLMs Into Single-File Executables

#mozilla #llm #ai #llama

https://hackaday.com/2023/12/02/mozilla-lets-folks-turn-ai-llms-into-single-file-executables/

happyborg, to Futurology
@happyborg@fosstodon.org avatar

I mean, wut?

User: make a list of things I might find you useful for

Llama: Sure, I'd be happy to help you with that. Please provide me with a list of things or tasks you would like assistance with and we can work together on them.

It took nearly a minute of hammering my eight CPU cores to come up with that. 🤷‍♂️

I think we're safe from for the foreseeable. Don't listen to twerps like who is just shilling.

happyborg, to llm
@happyborg@fosstodon.org avatar

Try a local #LLM using #Mozilla's #Llamafile:

  1. Get the 4.3GB file:
    curl -LO https://huggingface.co/jartine/llava-v1.5-7B-GGUF/resolve/main/llava-v1.5-7b-q4-server.llamafile

  2. Make executable

  3. Run it

  4. Visit http://127.0.0.1:8080/

You're welcome!

This is a text and image capable LLM, so ~ #ChatGPT 4

h/t @simon

More in Simon's blog: https://simonwillison.net/2023/Nov/29/llamafile/

happyborg,
@happyborg@fosstodon.org avatar

@simon
Has anyone found a use for #Llama #LLM (see above)?

Serious question. It's interesting to play with but I haven't found anything I'd use it for yet. The only thing it seems it may be good at is summarising a news page and articles filtered by subject - though I'm not sure that's really useful to me.

itnewsbot, to ArtificialIntelligence
@itnewsbot@schleuss.online avatar

Mozilla Lets Folks Turn AI LLMs Into Single-File Executables - LLMs (Large Language Models) for local use are usually distributed as a set of wei... - https://hackaday.com/2023/12/02/mozilla-lets-folks-turn-ai-llms-into-single-file-executables/

devinprater, to ai

Well, I'm sure an NVDA addon with this will be here soon. Just amazing how far things have come. I mean, I hope there's a Windows version of the Llava part of this anyway.

llamafile is the new best way to run a LLM on your own computer:

https://simonwillison.net/2023/Nov/29/llamafile/

#Llava #ai #Llama #LlamaFile #NVDA #windows

mike, to llm
@mike@jammer.social avatar

The wife and I had a good laugh today while I was experimenting with 's. Feeding a complex prompt that analyzes forum posts, it decided that her career in pharmacy is a crime. 🤣

mike,
@mike@jammer.social avatar

That said #Claude is still really good, I just need to find the right approach to make it act consistently. I doubt my problem is math, but it is mixing up numbers (0 is 10 is 0 is...). 🤔

I'd assume GPT-4 will work better, but the point is I'm trying to do stuff without OpenAI.

Right now I'm exploring if my idea is viable (it looks promisimg), then I'll move on to recreating it on #Llama and fine tuning.

pb, to llm French
@pb@mast.eu.org avatar

Mise à jour par rapport à mes vidéos précédentes du printemps.

Petit essai en vidéo de .5, un nouveau modèle de libre utilisable avec .cpp, et qui prétend être comparable à GPT 3.5 Turbo, l'avant-dernier modèle d'OpenAI.

La vidéo est aussi faite pour montrer ce que ça donne en rapidité sur un processeur "normal", sans usage du GPU.

(bugs compris : réalisé sans trucage).

https://peertube.eu.org/w/cMHfSKmJ5W2hd62ziiH8o9

SharonCummingsArt, to art
@SharonCummingsArt@socel.net avatar

Today's bit o' JOY!

50% OFF ALL apparel!

A COOL t-shirt with my ART on it for less than box stores. AND.............You are supporting an independent artist and farmer. :)

APPAREL HERE:
https://fineartamerica.com/profiles/sharoncummingsart/shop/tshirts

eclectech, to photography
@eclectech@things.uk avatar

What a day.

#photography #llama

devinprater, to ai

Welp, here we go. Be My Eyes is so great, people are just... Calling their projects Be My Eyes web apps now. Cause it's 2023 and here we are. No, I haven't tried this thing. I hope it's worth the absolute shitstorm of a hype train this will cause in the blind community once people get to looking at it.

https://github.com/lxe/llavavision

Polynomial_C, to ai Catalan
@Polynomial_C@mastodon.social avatar

#LLaMA 2 #AI
Picture from X
👍

art_history_animalia, to random
@art_history_animalia@historians.social avatar

More from Virginia Museum of Fine Arts visit:

  1. Stirrup Vessel in the Form of a
    Chavin (Peru), 500 BCE - 100 CE
    Terracotta w/ polychrome slips
  2. Stirrup Vessel in the Form of a
    Moche (Peru), 200-500 CE
    Terracotta w/ polychrome slips

Moche duck effigy vessel with stirrup spout on display at museum

marcel, to ChatGPT German
@marcel@waldvogel.family avatar

Ist es eine gute Idee, wenn wir eine unzuverlässige (übertölperbare, halluzinierende, …) auf unsere privatesten Daten loslassen? Und diesen KI-Sprachmodellen gegenüber sind wir erst noch besonders offenherzig. 1/2

https://www.heise.de/hintergrund/Warum-die-Wette-von-Big-Tech-auf-KI-Assistenten-so-riskant-ist-9326067.html

stungeye, to ai
@stungeye@mastodon.gamedev.place avatar

Have you seen LLaVA?

The Large Language and Vision Assistant is a multimodal (image & text) #ai model.

It's an open-source approach to visual & language prompting, combining a #ml vision encoder & a large language model (#Vicuna #LLaMA #llm).

It's surprisingly good!

🧵1/n

mikarv, to Futurology
@mikarv@someone.elses.computer avatar

Meta's #Llama 2 license has an unusual clause whereby they withdraw your right to use the model if you allege #Meta has breached your own IP rights by training their stuff on your intellectual property. #copyright #genai #LLama2

boilingsteam, to linux
@boilingsteam@mastodon.cloud avatar

Llama 2 Everywhere (L2E): Standalone, Binary Portable, Bootable Llama 2: https://github.com/trholding/llama2.c
#linux #update #foss #release #llama #standalone #binary #llm

BlueBlasphemy, to random
@BlueBlasphemy@mstdn.games avatar

You came to the wrong neighborhood…

#GamersTavernLlamasAndAlpacas #AlpacaMonday #Alpaca #Llama

s_mcleod, to llm

M.2 NVMe -> PCIe x16 + some dodgy cabling = Tesla P100 eGPU 😂

Combined with my RTX3090 I can load Q4/Q5 70b models 100% into vRAM with exllama or autogpqt

#LLM #AI #ML #Llama #Nvidia #GPT

image/png
image/jpeg
image/png

thomasfuchs, to random
@thomasfuchs@hachyderm.io avatar

Can’t wait for the “actually LLMs are a worthless scam” articles in 2025 and all the people that pretend they never fell for it

mazisworld,

@thomasfuchs noooo LLM'S ARE THE FUTURE.

We just can't afford to develop. What's going to happen is Governments are going to try and coin the technology and control masses with greater intensities.

For the private sector the development will stagnant because of corporate greed and lacking diversion.

Privatized AI is where the POWER IS.

Yet the government is the world's largest Private Power.

#AI #LLM #Llama #AltmanOverlord

joannaholman, to melbourne
@joannaholman@aus.social avatar

Only day 1 of the show and the llamas are already having an existential crisis

igisho, to Cat
@igisho@rockosbasilisk.com avatar

After week or so running @idiotbusiness bot i noticed that related topis are more frequent that others. Note that there is no cat related personality in or specific cat related prompt included in generating this content. Did made spinoff to world?

ricardoharvin, to random
@ricardoharvin@mstdn.social avatar

Climate change is an immediate threat to the majority of the world's population.

We need a local, regional, state, national, and international "moon shot" type of concentration of effort using available resources while developing and advancing new science and technologies to counteract the damage humans have caused.

Without this type of all-out, universal cooperation, human civilization, and perhaps humanity itself, are in imminent danger of extinction.

ricardoharvin,
@ricardoharvin@mstdn.social avatar

Every little thing that helps is part of the Everything, Everywhere, All at Once mitigation strategy.

"The work was done in collaboration with 2000 Asociación...local ...negatively impacted by the receding "
“...the ...not only requires...the authors, but all of these other groups...it shows the constant need for collaboration and to develop communities..."
with local involvement is key.
https://eldritch.cafe/@SallyStrange/111285235715183031

  • All
  • Subscribed
  • Moderated
  • Favorites
  • JUstTest
  • everett
  • DreamBathrooms
  • khanakhh
  • magazineikmin
  • tacticalgear
  • Youngstown
  • osvaldo12
  • slotface
  • ngwrru68w68
  • rosin
  • thenastyranch
  • kavyap
  • InstantRegret
  • provamag3
  • Durango
  • mdbf
  • tester
  • cisconetworking
  • ethstaker
  • modclub
  • GTA5RPClips
  • cubers
  • Leos
  • normalnudes
  • megavids
  • anitta
  • lostlight
  • All magazines