How to Install and test LLaMA 3 Locally [2024]

After the release of Llama3 i thought i should make a view to walk anyone who is looking to use it locally. i hope this video helps:)

Related links:

- - - - - - - - - - - - - - - - - - - - - -

Follow us on social networks:

---

#ai #artificialintelligence #llama3 #metaai #install #macos #machine #machinelearning #aitools #programming #softwaredeveloper #softwareengineer #webdeveloper #developer #iosdeveloper #mobiledevelopment #coding #coder #javascript #developer #computerscience #computersciencestudent #100daysofcode #html #css #programmer #vue #npmpackage #npm #package #CodeNewbies #Code_with_bro #code_withbro #youtubechannel #youtube #youtuber #youtubers #subscribe #youtubevideos #sub #youtubevideo #like #instagram #follow #video #vlog #subscribetomychannel #gaming #music #explorepage #love #smallyoutuber #vlogger #youtubegaming #instagood #llms #youtubecommunity #likes #explore #youtubelife #youtubecreator #ps #bhfyp #fotiecodes

[codewithbro]

Model variants

Instruct is fine-tuned for chat/dialogue use cases.
Example: ollama run llama3 ollama run llama3:70b

Pre-trained is the base model.
Example: ollama run llama3:text ollama run llama3:70b-text

[Knuhben]

Nice video! Can you do one on how to set up a local database out of pdf files? So the A.I would be able to search that pdfs and answer questions regarding the content

[SevScout]

I love how in the intro, we're being told about a new AI, by an old one.

[podunkman]

llama 3 in action:

>>> How many liters of water per minute can a Dutch windmill pump out?
That's an interesting question!

The answer depends on the specific design and size of the windmill. However, I can give you some general
information.

Traditionally, Dutch windmills are designed to pump water from shallow sources, such as polders or wells, for
irrigation purposes. The capacity of these windmills varies greatly, but a typical small to medium-sized windmill
might be able to pump around 0.5 to 2 liters per minute (L/min).

Some larger industrial-scale windpumps can pump much more, up to 10-20 L/min or even more, depending on the
turbine design and the pressure head of the water.

Really?

[anshulsingh]

what about hugginggface chat ui?
I recently installed ollama open webui, worked fine, after 1day I started getting some error in docker getting restarted because of some cuda error.

I don't want to trust it now because I cannot find a fix, although reinstalling fixed it.

And on terminal it was always working and working faster than web ui

[gallyyouko]

How can I run the original not_quantized version of llama 3-8B(It is almost 15gb)?

[BrandWorksApp]

how do you add your models I have ollma set up in my ps command line but when I used the UI it didnt show up and Idk how to upload them please help!

[LordeSam]

what if the model only uses CPU resources? it's very slow, it would be great to speed it up with a GPU

[SirDragonClaw]

How can I run the larger version of the model?

[Baly]

I didn't really get the part on docker, can you help me ?

[dylandsilva]

Is there a way to run it on custom developed UI? Can someone please guide me as to how?

[mattpears]

can i run this offline with NO DATA being sent for it to respond to user queries?

[GiochiamoinsiemeadAndrydex]

How to change the location of the insallation and the location of the download of the model?

[PedroHenriquePS]

why do all of these dont have a proper graphical interface... i hate having a black screen to stare at

[cptcrogge]

I'm glad that my PC handles 70B with 16GB VRAM and 64GB of RAM. I wonder what the absolute minimum requirements are for 400B.

[benbork]

stop click baiting, the 400b is not even out

[Ligthus]

Advice: use powershell and not git bash 🤣

[viniciusmelo]

content is fine, but your explanation wise