NVIDIA's Nemotron-4's is totally insane for synthetic data generation

  Рет қаралды 1,816

Chris Hay

Chris Hay

Күн бұрын

the nvidia nemotron-4 340 billion parameter models are brand new open source models from nvidia that you can use to generate your own synthetic data. in this video chris shows you how to get started with nvidia cloud and nvidia nim services. using nvidia cloud you can use all the major open source and commericial models such as llama3, mistral, google and ibm granite models. in this video we focus on the new nvidia nemotron instruct and reward models showing how you can use the models to generate synthetic data, and judge the outputs using the reward model. even if you're not interested in training models, the nvidia cloud is very fast for training and inference of ai models.

Пікірлер: 17
@erfanshayegani3693
@erfanshayegani3693 3 ай бұрын
Your videos help me a lot stay up-to-date with the latest stuff. This video for example, led me to these new reward models and datasets that have been released only a few days ago! I think if you can also have some 10 min videos weekly to summarize the important releases and new stuff it would be great! Many thanks for the great content again!
@chrishayuk
@chrishayuk 2 ай бұрын
Sadly, 10 mins weekly summary videos isn’t my style. Check out the IBM mixture of experts podcast though, I’m usually on every 4 weeks or so
@pratiknarendraraut6889
@pratiknarendraraut6889 3 ай бұрын
igrore the dude below, awesome content , keep going .
@chrishayuk
@chrishayuk 3 ай бұрын
Appreciate it!
@sidharthrao9005
@sidharthrao9005 3 ай бұрын
Is there any possiblities to fine-tune, quantise or distill the model into a smaller model to be run locally? I urgently need this for a project I'm doing.
@chrishayuk
@chrishayuk 2 ай бұрын
i'm not aware of anyone that has done this tbh, it's quite a large model. and it'd be a challenge to get it small enough
@bamh1re318
@bamh1re318 3 ай бұрын
what kind of hardware requirement do I need to run this? Thanks!
@chrishayuk
@chrishayuk 3 ай бұрын
more than most can afford, it really needs to be run on cloud. i think it's like a cluster of 8 x H100's or something to run it, not sure off the top of my head
@richsoftwareguy
@richsoftwareguy 3 ай бұрын
Maybe you need new glasses. Your eyes keep getting stuck together, hella annoying.
@everyhandletaken
@everyhandletaken 3 ай бұрын
How respectful of you. There are other channels, if you can't cope.
@chrishayuk
@chrishayuk 3 ай бұрын
lol, tell me about it, I have a light sensitivity hence why I wear the glasses. I don’t think anything but my sunglasses will fix that, sadly
@WillJulian-Vicary
@WillJulian-Vicary 3 ай бұрын
@@chrishayuk Ignore the troll, thought your video was great - thanks for sharing.
@chrishayuk
@chrishayuk 3 ай бұрын
thank you, appreciate it
@chrishayuk
@chrishayuk 3 ай бұрын
thank you, appreciate it
The future of AI agents is WebAssembly (get started now)
39:51
Chris Hay
Рет қаралды 1,8 М.
i really want to say goodbye to copilot...
35:21
Chris Hay
Рет қаралды 2,4 М.
Don't look down on anyone#devil  #lilith  #funny  #shorts
00:12
Devil Lilith
Рет қаралды 40 МЛН
Когда отец одевает ребёнка @JaySharon
00:16
История одного вокалиста
Рет қаралды 11 МЛН
What is Retrieval Augmented Generation (RAG) and JinaAI?
37:12
Chris Hay
Рет қаралды 3,2 М.
Postgres just got even faster
26:42
Hussein Nasser
Рет қаралды 34 М.
Fine-Tune Llama3 using Synthetic Data
37:03
Chris Hay
Рет қаралды 3,1 М.
Eric Weinstein - Are We On The Brink Of A Revolution? (4K)
3:29:15
Chris Williamson
Рет қаралды 7 МЛН
NixOS Setup Guide - Configuration / Home-Manager / Flakes
3:01:39
Matthias Benaets
Рет қаралды 194 М.
Don't look down on anyone#devil  #lilith  #funny  #shorts
00:12
Devil Lilith
Рет қаралды 40 МЛН