Build your own local o1 - here’s how

  Рет қаралды 57,903

David Ondrej

David Ondrej

Күн бұрын

Пікірлер
@DavidOndrej
@DavidOndrej Ай бұрын
Wanna build your own AI Startup? Go here: www.skool.com/new-society
@startingoverpodcast
@startingoverpodcast Ай бұрын
Why aren't you using Msty?
@aaaaaaaaooooooo
@aaaaaaaaooooooo Ай бұрын
Wait, my data is not private with o1? I didn't know that. Where can I check this? Where is this notified to the user, or did they bury it in small text?
@indiemusicvideoblog
@indiemusicvideoblog Ай бұрын
Great! Now build a local agent with lama that can control your computer like Antropic
@orthodox_gentleman
@orthodox_gentleman Ай бұрын
Very doable with Open-Interpreter which is open source and free
@Bllakez
@Bllakez Ай бұрын
@@orthodox_gentleman How much should I pay someone to setup for me?
@alexrayoalv
@alexrayoalv Ай бұрын
I literally did this 6 months ago.
@anubisai
@anubisai Ай бұрын
You build it.😂
@marilynlucas5128
@marilynlucas5128 Ай бұрын
Skyvern!
@samimejri8079
@samimejri8079 Ай бұрын
I just used Llama 3.2 locally and asked about starting a 3d printing business as a 3D beginner. It gave a similar output of what you spent a good time building in this video... Maybe do it the next time, show a before and after response from an LLM.
@bossgd100
@bossgd100 Ай бұрын
😂
@DCinzi
@DCinzi Ай бұрын
There is a model called Llama3.3B-Overthinker. I think it would fit the task quite nicely.
@JackGamerEuphoriaDev
@JackGamerEuphoriaDev Ай бұрын
Is there available in Ollama or hugging face? If you don't mind the question. Thanks by the way for giving directions..
@chrystofferaugusto1194
@chrystofferaugusto1194 Ай бұрын
Btw, the concept you reached in this video of undetermined number of agents is far superior than it was from a video from 5 days ago. Really awesome 👏🏻
@godned74
@godned74 Ай бұрын
You could try "When providing responses, use concise and primary representations. However, include additional details only when needed to ensure clarity and completeness of the task" and you should get short response's with out compromising the chain of thought.
@eviv8010
@eviv8010 Ай бұрын
nice clickbait
@kylev.8248
@kylev.8248 Ай бұрын
It’s not clickbait tho
@bruce_x_offi
@bruce_x_offi Ай бұрын
@@kylev.8248 You must be King of fools
@mihaitanita
@mihaitanita Ай бұрын
So, you've used Claude 3.5 (2024 october update) within Cursor AI Editor to develop a (simple) python script that run some agenting on a 70b model on ollama? Where's the o1 in here?
@Dancoliio
@Dancoliio Ай бұрын
o1 is a reasoning model which kept their reasoning 'recipe' private. This is his take (which resonates with the average user of locally owned open source models) to kind of hack the way the 70b model works and simulate reasoning to enhance the final output> a simple method which actually does provide better replies.
@BikramAdhikari89
@BikramAdhikari89 Ай бұрын
He is not sharing his research paper published in arxiv my man.
@MrMoonsilver
@MrMoonsilver Ай бұрын
Cool new format with the presentation man
@bsiix1576
@bsiix1576 Ай бұрын
Maybe I missed it, but what hardware is needed for that nemotron - it is 43GB? Doesn't that mean you need at least that much VRAM? And here I thought I was a baller with my 16GB vram...
@mariomanca7546
@mariomanca7546 Ай бұрын
If you instruct the agent to use the fewest possible lines, it's likely to eliminate comments, which is suboptimal but expected.
@foxusmusicus2929
@foxusmusicus2929 Ай бұрын
Great video. Which hardware specs do you have? :-)
@AK-ox3mv
@AK-ox3mv Ай бұрын
How much you'r local O1 results has more accuracy in comparison to original nemotron 70b and llama 3 3b without uaing chain of thought? Was there any improvement in bechmarks like Humaneval and MMLU?
@Plife-507
@Plife-507 Ай бұрын
I want to build an agent swarm to do coin margined futures btc trading. With each agent handing a serpearte part, ta, market sentiment, execution, risk tolerance, is there a way to keep each model small and only train it to focus on its task?
@FrankDecker-n9e
@FrankDecker-n9e Ай бұрын
@DavidOndrej, what is your Mac specs? I have a Macbook Pro M3 Max 48 GB..
@KiranMohan-dpthinkr
@KiranMohan-dpthinkr Ай бұрын
Hey David, how can we reassure clients that their data is secure and won't be shared with the LLM provider for internal training purposes? What steps can we take to ensure their data privacy and address any concerns they might have?
@cdunne1620
@cdunne1620 Ай бұрын
You d to ask that in David’s classroom at skoool
@KiranMohan-dpthinkr
@KiranMohan-dpthinkr Ай бұрын
@@cdunne1620 Sure
@haljohnson6947
@haljohnson6947 Ай бұрын
He mentions that in the video like four times
@KiranMohan-dpthinkr
@KiranMohan-dpthinkr Ай бұрын
@@haljohnson6947 can you mention the specific timeline where he described about it.
@KiranMohan-dpthinkr
@KiranMohan-dpthinkr Ай бұрын
@@haljohnson6947 pls mention the timeline where he mentioned it.
@michaeltse321
@michaeltse321 Ай бұрын
You downloade nemotron and not the 70b version which is why you had the error
@qkb3128
@qkb3128 Ай бұрын
Would have loved to check this out yet I don’t have that kinda money to spend to see the code. Good luck to ya .
@costatattooz840
@costatattooz840 Ай бұрын
locally what hardware do you need to run this at minimum? i have a 64gb ram + 3060 12gb
@ticketforlife2103
@ticketforlife2103 Ай бұрын
Watch the video
@H3XM0S
@H3XM0S Ай бұрын
You'll need over 40gb vram so like 2 x rtx 4090 might be a good option. No idea what hardware is being used in the video. Anyone saying 'watch the video' should provide a timestamp.
@bollvigblack
@bollvigblack Ай бұрын
this guys is rich. not even joking so
@chrystofferaugusto1194
@chrystofferaugusto1194 Ай бұрын
He is on a MacBook Pro bro…
@skeyenett
@skeyenett Ай бұрын
64GB RAM + 4070 Ti Super (16 VRAM) = Run Nemotron-70b-instruct-q2_K
@Luxcium
@Luxcium Ай бұрын
😂 I love the way you have called out your mistake 4:00 it was just so delightful to see you handle it like a boss that I have had to replay it more than 3 times to enjoy the moment... You are definitely a smart man!!! I am eager to see the evolution over time!!! 😅
@dark_cobalt
@dark_cobalt Ай бұрын
Already have it lol. Running it on my RX 7900XTX with q4m, but i think ill buy myself 1-2 Radeon W7900 Pro to gain a lot more performance. Alsp you don't need Ollama for it, because it's available in LM Studio and it's downloading from Huggingface. Btw what PC hardware specs do you have?
@rhadiem
@rhadiem Ай бұрын
He's clearly using a 128gb Macbook Pro which can use the memory as vram. He's running un-quantized. How much vram do you have on your gaming gpu? Nobody asked about your hardware bro.
@dark_cobalt
@dark_cobalt Ай бұрын
@@rhadiem Every PC can use the RAM as VRAM. It's how computers work. It's called virtual memory. If the VRAM fills up, the computer uses the RAM as backup memory, to stay stable and not crash. But the RAM is waaaaaaay slower than the VRAM, that's why I am asking him what specs he has. My GPU has 24GB of VRAM and even with the Quant 4M (around 32GB) model of Nemotron 70B my VRAM gets filled up completely and my RAM also to 50GB, which slows down the model to such an amount, that it's painfully slow. He is using a way bigger model, without any issues. If he has a GPU with this huge amount of VRAM, this would be totally understandable, but with the RAM? I don't understand why lol. 😄
@TheDarkLordAngel
@TheDarkLordAngel Ай бұрын
That mark on your nose-it’s almost like a signature, something that’s so naturally you.🖖👍
@orthodox_gentleman
@orthodox_gentleman Ай бұрын
Dude, there are very few people that can run nemotron locally….
@hrarung
@hrarung Ай бұрын
awesome video David! How to train this model based on my dataset? and How to give it a nice UI?
@aaaaaaaaooooooo
@aaaaaaaaooooooo Ай бұрын
Are my prompts on o1-preview used to train the AI even if I opt out? Where do I find this information?
@TheAsianDude9999
@TheAsianDude9999 Ай бұрын
What vscode extension are you using for your ai?
@borick2024
@borick2024 Ай бұрын
Have you had a chance to compare your results against GPT4o?
@MrAndrew535
@MrAndrew535 Ай бұрын
I want to preserve a million-word dialogue between myself and my ChatGPT on multiple threads while upgrading to your recommendations. How do I achieve that?
@szebike
@szebike Ай бұрын
Nice, your contribution to the open source community is awesome!
@ysh7713
@ysh7713 Ай бұрын
opensource?
@szebike
@szebike Ай бұрын
@@ysh7713 Well kind of ~ better than giving all you data to a faceless big company who wills steal your data 100%.
@hotlineoperator
@hotlineoperator Ай бұрын
I have test o1 - and it is not so smart. People still need to quide its selections. Big problem with models is censorship, someone else have select what you can do and not to do with these tools.
@Visualife
@Visualife Ай бұрын
You should use Anything LLM and docker / Open WebUI
@rafaelortega1376
@rafaelortega1376 Ай бұрын
No repo to share the code?
@EtH-xf6br
@EtH-xf6br Ай бұрын
What a beast Macbook you need to have to get such a fast response. I have 7800x3D and 4080 rtx and its waaay slower.
@danieleduardo9800
@danieleduardo9800 Ай бұрын
How’d you get composer in the sidebar?
@Bakobiibizo
@Bakobiibizo 26 күн бұрын
A terminal?! I'm freaking out man
@gauravrewaliya3269
@gauravrewaliya3269 Ай бұрын
How to make local ai with backpropogation feature ( if got wrong stuff, CEO instruct what's wrong and it improve sub local agent by time )
@devbites77
@devbites77 Ай бұрын
Inspiring stuff. Cheers!
@MiNiD33
@MiNiD33 Ай бұрын
"Comments are apologies in code." - Robert C Martin. Cursor is helping you. Also for the price of the spec of this machine, you can buy an insane number if tokens from anthropic or openai. It might be worth getting people started using a hosted service.
@jefferystartm9442
@jefferystartm9442 Ай бұрын
Brooooo , there are tools you are behind on . Agent s and Claude computer use?? E2B has an open source version tooo 😊 stay blessed Ondrej
@VinceOmondi
@VinceOmondi Ай бұрын
Good stuff, Ondrej!
@SjarMenace
@SjarMenace Ай бұрын
why do you have that thing on your nose?
@babyjvadakkan5300
@babyjvadakkan5300 Ай бұрын
For correcting the nasal path/nose bridge (or something like that
@INeedMeme
@INeedMeme Ай бұрын
More oxygen bro
@cdunne1620
@cdunne1620 Ай бұрын
Soccer players used to wear them years ago for example Robbie Fowler for Liverpool
@AGINews-TogethWithAI
@AGINews-TogethWithAI Ай бұрын
exactly what I needed thank you so much David🎉
@FuZZbaLLbee
@FuZZbaLLbee Ай бұрын
You can also use the ollama streaming output to generate text. This way you know what’s the generator is doing. Also I think that GPT o1 does more then split up a task and let agents fix the individual tasks. But nevertheless, a nice tutorial on making agents.
@zechariahprince5671
@zechariahprince5671 Ай бұрын
We have had AGI for over a year.
@11metatron11
@11metatron11 Ай бұрын
Not a chance with my elderly MacBook Pro. Looks like I need some new gear…
@jayhu6075
@jayhu6075 Ай бұрын
What a great explanation. Thnx
@eado9440
@eado9440 Ай бұрын
🎉 you actually made it. Thanks
@gaelfalez
@gaelfalez Ай бұрын
Missing the comparison between result using multiple agents and result using just 1.... Disappointing. We Don t even know if it is worth the work....
@skulltrick
@skulltrick Ай бұрын
Very inspiring! Thanks
@aatheraj1667
@aatheraj1667 Ай бұрын
Yet, we don't one that could trade Nasdaq futures.
@olivert.7177
@olivert.7177 Ай бұрын
There is also an nemotron-mini model which is only 4b.
@samuelgarcia1802
@samuelgarcia1802 Ай бұрын
How good it is? In hugging face I saw nematron was in a bad place
@orthodox_gentleman
@orthodox_gentleman Ай бұрын
Really??? Omg that is great
@aljosja3353
@aljosja3353 Ай бұрын
Which computer u can use for local llm
@Gamatoto2038
@Gamatoto2038 Ай бұрын
strong pc
@MrMoonsilver
@MrMoonsilver Ай бұрын
Also, I hope the bruise on your nose heals soon. Been a long time now.
@Tetardo
@Tetardo Ай бұрын
I think it’s a medical device that helps him breathe
@avi7278
@avi7278 Ай бұрын
Oh yeah im sure openai is quaking in their boots, bro.
@chrystofferaugusto1194
@chrystofferaugusto1194 Ай бұрын
You should have a discord community to people share projects and business
@chrystofferaugusto1194
@chrystofferaugusto1194 Ай бұрын
Never mind, now I got the business model on skool. Nice call, thinking about joining it
@SCHaworth
@SCHaworth Ай бұрын
No. Not quite. You have to split the turns.
@claxvii177th6
@claxvii177th6 Ай бұрын
1 token per second is too slow for any pratical use...
@slt
@slt Ай бұрын
Dadusak!
@supermandem
@supermandem Ай бұрын
Bro llama is nowhere near o1 wtf
@sushilsharma1621
@sushilsharma1621 Ай бұрын
clickbait or misleading title
@blasterzm
@blasterzm Ай бұрын
Lol, that's not how O1 works. You can't tell it in the system prompt
@themax2go
@themax2go Ай бұрын
modern day sham(mer) 👍
@dorukkurtoglu
@dorukkurtoglu Ай бұрын
27:36 LOL🤪
@immortalityIMT
@immortalityIMT Ай бұрын
Cool!
@Álvaro-o5e
@Álvaro-o5e Ай бұрын
99% of free stuff sucks. One of them is this video. 20 minutes to answer "why is the sky blue?"
@overunityinventor
@overunityinventor Ай бұрын
free stuff has a learning curve, it's not everyone's cup of tea
@tomwawer5714
@tomwawer5714 Ай бұрын
99% of paid software sucks and it hurts your wallet
@adithyansreeni7491
@adithyansreeni7491 Ай бұрын
i fkin slep bro
@gustavramedies2901
@gustavramedies2901 Ай бұрын
David i would like to create sales agents,lead generators,receptionist,appointment setters and I want to sell them.Can you help 😢
@ShishuSud
@ShishuSud Ай бұрын
😇
@EduardoAlarconGallo
@EduardoAlarconGallo Ай бұрын
Title is misleading. You are using Llama which is a LLM but not a Reasoner model
@surendarreddys7298
@surendarreddys7298 Ай бұрын
1st one to comment 😄
@HimaLoubi
@HimaLoubi Ай бұрын
😂 you need a graphic card with a price of a Tesla car to run that module locally ; btw you talk like 10.000word/min , 😅
@TheBhushanJPawar
@TheBhushanJPawar Ай бұрын
I am getting following error: bhushan@Bhushans-MacBook-Pro ~ % ollama run nemotron Error: llama runner process has terminated: signal: killed
@TheBhushanJPawar
@TheBhushanJPawar Ай бұрын
After clearing some memory now it's started working...
@stefanschz7589
@stefanschz7589 Ай бұрын
Awesome!
"Build an AI startup in 2025!" - Professional AI agent developer
51:50
Гениальное изобретение из обычного стаканчика!
00:31
Лютая физика | Олимпиадная физика
Рет қаралды 4,8 МЛН
“With o1 you can code any app, just watch” - Pietro Schirano
39:46
Run your own AI (but private)
22:13
NetworkChuck
Рет қаралды 1,7 МЛН
Ultimate Guide to AI Agent Platforms: Which One is Best for You?
17:19
Build anything with bolt.new, here’s how
21:15
David Ondrej
Рет қаралды 142 М.
Build Anything with AI Agents, Here's How
29:49
David Ondrej
Рет қаралды 329 М.
host ALL your AI locally
24:20
NetworkChuck
Рет қаралды 1,5 МЛН
Qwen Just Casually Started the Local AI Revolution
16:05
Cole Medin
Рет қаралды 117 М.
This is how I scrape 99% websites via LLM
22:44
AI Jason
Рет қаралды 178 М.