How much compute does this require? I don't want to make a big llm
@tdi-India7 күн бұрын
Really amazing 🎉
@msjchr92211 күн бұрын
Hi, in my opinion, instead of using print() to debug, using breakpoint() or import pdb; pdb.set_trace() would be more easier to debug your code! try it out :)
@kyegomez324210 күн бұрын
thanks for the tip, need to share that! Are you in the community: discord.com/servers/agora-999382051935506503
@BasitMustafa11 күн бұрын
You make a valid point about the knowledge acquisition gap in general. What concerns me about how we are discussing and socializing AI is the leap from that valid point to cognition & practice. From knowledge to practicing doctor/medicine is an enormous leap. AI no doubt can be an important part of this, but the parallels (both direct and indirect) drawn here about time in med school/residency vs what AI could do fundamentally discounts that med school (or any other type of training) is actually far less about knowledge acquisition as it is about practice. I know what it takes to run a 4 minute mile. But can I? I wish. I don’t think you were making that kind of a claim but I think it risks coming across that way.
@WirelessGus13 күн бұрын
🔥
@mikew288314 күн бұрын
Good stuff! 👏
@kyegomez324214 күн бұрын
Appreciate it ;) means alot 😆
@MindStarsSoulStops22 күн бұрын
I look forward to more of the content. but as an audio engineer... I can not stress how important it is for good audio on KZbin. You will lose so many people in seconds just because you didn't do EQ.
@mikew288327 күн бұрын
AI Vocal Trance 😄👍
@kyegomez324226 күн бұрын
Yeah playlist is fire
@WirelessGus29 күн бұрын
I love to see young men hustling! #Kaizen, Your desire to learn and teach is invaluable! #LLM #Architecture #Future
@yebinianhiАй бұрын
the input_dim and output_dim must be the same, otherwise, the program failed.
@kevinhe7Ай бұрын
You need 2 more screens
@VarshaShirole-vz8fkАй бұрын
Great Work
@idrees2516Ай бұрын
subtitles are showing but voice is not coming only music is audible
@Emerson1Ай бұрын
Cool
@infraiaАй бұрын
Nice
@kyegomez3242Ай бұрын
thanks!!!
@SreeramAjayАй бұрын
Great content, get well soon @KyeGomez Thanks for sharing. Can you also please write code for training and a simple example to show its effectiveness.
@DA-rb4sjАй бұрын
Hope you get better soon
@jvboidАй бұрын
thanks. get well
@chamber35932 ай бұрын
Intro could have been Elevenlabs api call in Sam Elliott voice. Great Idea and execution. more vids.
@ecotextileStudio2 ай бұрын
happy with yet again, another super channel! 👏👏👏
@fariskapo83652 ай бұрын
"Taxes and weird stuff like that" hahahah
@user-wr4yl7tx3w2 ай бұрын
problem is that they don't work
@kyegomez32422 ай бұрын
can you explain more? how exactly? do you have some test code
@josephmargaryan2 ай бұрын
Just heard about the mamba model and was trying to build a simple one from scratch. Thank you for your video and do you think these can be used for other tasks beside nlp?
@kyegomez324210 күн бұрын
Thanks for the comment and hoped you enjoyed it. Yes, it can be used for time series forcasting and much more!
@BienestarMutuo2 ай бұрын
Nice, setup a web page to use that online, because i dont want to spend time trying to setup or update that, charge for use, give a first 5$ free to try, use opensource LLMs, and optional corporate ai models, let the people use it. Dont use any user data for training, privacy is very important, make the note to the user that corporate ai is not private.
@kiffsimon-pm6ix2 ай бұрын
Yeahhhhhhhh
@BienestarMutuo2 ай бұрын
Why not incorporate something like Actor Model, kzbin.info/www/bejne/e33adpeYlNV3Zs0si=B4tK4_-w2uTGXNnn , that will bring fault tolerance. Thanks Kye for make your videos more short, we dont have time to see hour long videos.
@kyegomez32422 ай бұрын
Very interesting and yeah let's do it! And, yes, will do another one coming today.
@nomnom9143 ай бұрын
discord link expired, u need to generate the without expiry one
@kyegomez32422 ай бұрын
yeah, smh that keeps happening. Appreciate you lmk! discord.gg/P7Hb9dWx
@jmanhype13 ай бұрын
dspy in the hishoussee!!
@kyegomez32423 ай бұрын
need to learn more about it
@ZelinHe-kw8hi3 ай бұрын
In general a good video. Learned how it is like when experimenting with a new architecture.
@kyegomez32422 ай бұрын
Glad you enjoyed it! stay in tune!
@Spas20114 ай бұрын
this random zoom effect is really annoying.
@kyegomez32422 ай бұрын
my bad. ill fix it
@briancase95274 ай бұрын
Bzzt. GQA was used in LLaMA-2, so it's not "in the last six months or so."
@Jeff-bf6dz4 ай бұрын
3:02 "A query is like a Google search, a value is like a web page, and a key is like the title." Bruh. I was a Senior Software Engineer at Google for over 11 years. What you are saying makes literally no sense.
@mmx27314 ай бұрын
Ah, I see a fellow tardigrade enthusiast (I'm only mildly joking).
@impactframes4 ай бұрын
Dude what happened to your amazing hair it was so original😭
@kyegomez32424 ай бұрын
I appreciate you, I took the naziretic vow and came into contact with a fallen Human. I must re-commence the holy ritual.
@impactframes4 ай бұрын
@@kyegomez3242 I hope you are able to complete it next time. Also thank you for the tutorial It was an interesting watch.
@DanielByrneReal4 ай бұрын
Thanks @kyegomez3242. Great summary description.
@attack_or_die42094 ай бұрын
Impressive model, thanks for the video.
@kyegomez32424 ай бұрын
Thanks for watching!
@ucalyptus24 ай бұрын
incredibly based
@gian34404 ай бұрын
Can't wait for the next videos in the series!
@donnychan19994 ай бұрын
why is the voice so corrupted?
@jianchiwei53794 ай бұрын
Your screen changes are too fast and not feeling stable and watchable.
@kyegomez32422 ай бұрын
Yeah, definitiely will take into account and optimize my future videos
@faridsaud6567Ай бұрын
Yeah, maybe just don’t zoom in? KZbin now allows to zoom in, so maybe it’s better to avoid it altogether
@kyegomez324210 күн бұрын
@@faridsaud6567 thats screen studio, the recorder
@kyegomez32425 ай бұрын
TIME TO ACCELERATE 🚀
@irrelevantdata5 ай бұрын
Weird... my reply is not able to be shown? Did you hide it or something?
@irrelevantdata5 ай бұрын
Chill tunes, btw.
@irrelevantdata5 ай бұрын
This is great! Cannot wait to try this out on my 3090.
@jonathanpadilla38885 ай бұрын
Huge
@deeplearningpartnership5 ай бұрын
Cool.
@JulianHarris5 ай бұрын
I've been working on something similar and the real problem with using LLM output as input into any kind of education is the grounding. There's little point in creating a curriculum that has hallucinations in it. It seems to me that one companion to a swarm would be a fine-tuning capability with accompanying data source that ensures that the output is grounded in fact. Maybe one way to do this could be to have a list of URLs of websites to crawl to feed into a fine tuning task, after which the curriculum is generated. Maybe the accompanying with a domain-specific HIT that validates output.
@brianboynton4105 ай бұрын
Is the language model learning to improve and if so is the policy dictated?
@tyrock50358 ай бұрын
With the right models this could be big
@jenniferh.72198 ай бұрын
I think the first thing to do when speaking to another person to find out if they are truly paying attention, is to randomly sprinkle 'multimodal tree of thoughts' every once in a while and nonchalantly continue. Just say it every once in a while, it's like a mini vitamin for your soul
@jenniferh.72198 ай бұрын
+ apparently not only are there multimodal tree of thoughts but ' multimodal autonomous agents'. A genuine way to not get someone to believe you are paranoid
@jenniferh.72198 ай бұрын
I guess I'm still learning things. With all due respect am I the only one asking, what the hell is this? I need a cliff notes, I don't know what I'm looking at and what it's for. I missed the intro. This is a foreign world