🚀 Free Llama 3.3 70B Model Tutorial: Groq Cloud Setup Guide

[00:01] hello guys U welcome to another episode

[00:04] of AML talks so today we will be talking

[00:06] about uh Lama models so llama is a like

[00:10] know open source model by Facebook or

[00:12] you can say Meta Meta so llama like know

[00:16] provides the weights and everything so

[00:18] you can either download the models if

[00:20] you have enough resources uh if you

[00:22] don't have resources and if you want to

[00:24] try llama you can go to meta you can

[00:27] click here so it will redirect you to

[00:29] meta

[00:30] and you can try it out so these llama

[00:33] versions they that they are using

[00:35] currently 3.1 so let's just ask it out

[00:38] which llama

[00:41] version are you currently

[00:49] using see it's currently using 3.1 but

[00:54] meta has released like 3.3 also so that

[00:57] you can use directly like you know so

[01:00] llama you can see llama has used uh

[01:02] released 3.2 and 3.3 also so to use that

[01:06] you can use cloud service called like

[01:09] you know grock Cloud uh so let's go to

[01:12] grock cloud and then we'll

[01:16] see so here you can like you know uh you

[01:19] can also test it out here whatever

[01:21] versions you wish to test it out so

[01:23] there are like Lama 3.1 3.2 so 3.3 is

[01:27] also there but I think that is there

[01:29] through the API part okay so uh what you

[01:32] can do is like you can go to API Keys

[01:35] like know go to like console. gro.com

[01:38] and create an account there uh it's a

[01:40] free thing right now and you can go and

[01:43] create an API out there and that API

[01:46] will give you access uh to llama new

[01:49] latest versions so Lama 3.3 is also

[01:52] available out there so after creating an

[01:54] API key you need to go to the

[01:56] documentation so in the documentation

[01:58] part uh like you know you can see how

[02:01] you can start working with like know Gro

[02:03] API uh so there are like API differences

[02:05] available out there so you can click on

[02:07] API references or you can if you want to

[02:09] just quick start here so you can go here

[02:12] and from there select the python part

[02:14] and copy it out okay and then you can

[02:17] use it in your uh system so like you can

[02:20] use it in collab or any any place you

[02:22] wish to do or any ID that you have so I

[02:25] am currently using vs code so I will

[02:27] show in the vs code part so uh I've just

[02:31] copied it out here and pasted it the

[02:33] whole thing is pasted already so uh I've

[02:36] added two extra things that were not

[02:38] there import OS and import from EnV

[02:41] import do uh load. EnV because these two

[02:45] things are uh required to get this um

[02:48] like know key that Gro API key so that

[02:51] API key you need to have it in EnV file

[02:53] from where you can uh call it out okay

[02:56] and then it's just same like you know

[02:58] everything else so here you need to

[03:00] mention the model which model you are

[03:02] using So currently this is a sample of

[03:05] Lama 3 8 billion so you can if you wish

[03:08] to use like any other thing uh like know

[03:11] you can just uh check the model cards

[03:13] out there and use it you can use mral or

[03:16] anything so that's not an issue okay so

[03:19] let's see like you

[03:21] know uh how it works so what we will do

[03:24] we will uh start with our virtual

[03:27] environment to my virtual environment is

[03:29] Gro EnV SL

[03:33] bin SL

[03:36] activate Okay now we need to just run it

[03:41] python

[03:43] gr Lama sorry Gro Lama

[03:49] dop yeah so see how fast it is so Gro

[03:53] Gro has like you know uh uh one of the

[03:56] best lpus so they are having like a

[03:58] language processing unit

[04:00] out there and uh they have the fastest

[04:03] response time uh of any of the cloud

[04:05] that is available as of now uh so you

[04:08] can see the how they have answered so

[04:10] fast language models have become like an

[04:12] increasing important today's landscape

[04:14] to do their ability to quickly process

[04:15] and generate large amount of natural

[04:17] data so this is how it is okay so uh

[04:21] like you know I hope you'll start

[04:22] building something out of it and you can

[04:25] go to gro.com sign up and get the key

[04:28] and start using any of the LM that you

[04:30] wish to use it there are multimetal

[04:33] versions also that also you can use okay

[04:36] I hope you have liked uh like my video

[04:38] so do like share and subscribe thank you

[04:41] everyone