subtitles are showing but voice is not coming only music is audible
@Emerson15 күн бұрын
Cool
@infraia6 күн бұрын
Nice
@kyegomez32426 күн бұрын
thanks!!!
@SreeramAjay16 күн 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-rb4sj16 күн бұрын
Hope you get better soon
@jvboid16 күн бұрын
thanks. get well
@chamber359323 күн бұрын
Intro could have been Elevenlabs api call in Sam Elliott voice. Great Idea and execution. more vids.
@ecotextileStudioАй бұрын
happy with yet again, another super channel! 👏👏👏
@fariskapo8365Ай бұрын
"Taxes and weird stuff like that" hahahah
@user-wr4yl7tx3wАй бұрын
problem is that they don't work
@kyegomez3242Ай бұрын
can you explain more? how exactly? do you have some test code
@josephmargaryanАй 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?
@BienestarMutuoАй 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-pm6ixАй бұрын
Yeahhhhhhhh
@BienestarMutuoАй бұрын
Why not incorporate something like Actor Model, kzread.info/dash/bejne/d4Crp8abj9OqYM4.htmlsi=B4tK4_-w2uTGXNnn , that will bring fault tolerance. Thanks Kye for make your videos more short, we dont have time to see hour long videos.
@kyegomez3242Ай бұрын
Very interesting and yeah let's do it! And, yes, will do another one coming today.
@nomnom914Ай бұрын
discord link expired, u need to generate the without expiry one
@kyegomez3242Ай бұрын
yeah, smh that keeps happening. Appreciate you lmk! discord.gg/P7Hb9dWx
@jmanhype12 ай бұрын
dspy in the hishoussee!!
@kyegomez32422 ай бұрын
need to learn more about it
@ZelinHe-kw8hi2 ай бұрын
In general a good video. Learned how it is like when experimenting with a new architecture.
@kyegomez3242Ай бұрын
Glad you enjoyed it! stay in tune!
@Spas20112 ай бұрын
this random zoom effect is really annoying.
@kyegomez3242Ай бұрын
my bad. ill fix it
@briancase95273 ай бұрын
Bzzt. GQA was used in LLaMA-2, so it's not "in the last six months or so."
@Jeff-bf6dz3 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.
@mmx27312 ай бұрын
Ah, I see a fellow tardigrade enthusiast (I'm only mildly joking).
@impactframes3 ай бұрын
Dude what happened to your amazing hair it was so original😭
@kyegomez32423 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.
@impactframes3 ай бұрын
@@kyegomez3242 I hope you are able to complete it next time. Also thank you for the tutorial It was an interesting watch.
@DanielByrneReal3 ай бұрын
Thanks @kyegomez3242. Great summary description.
@attack_or_die42093 ай бұрын
Impressive model, thanks for the video.
@kyegomez32423 ай бұрын
Thanks for watching!
@ucalyptus23 ай бұрын
incredibly based
@gian34403 ай бұрын
Can't wait for the next videos in the series!
@donnychan19993 ай бұрын
why is the voice so corrupted?
@jianchiwei53793 ай бұрын
Your screen changes are too fast and not feeling stable and watchable.
@kyegomez3242Ай бұрын
Yeah, definitiely will take into account and optimize my future videos
@kyegomez32423 ай бұрын
TIME TO ACCELERATE 🚀
@irrelevantdata3 ай бұрын
Weird... my reply is not able to be shown? Did you hide it or something?
@irrelevantdata3 ай бұрын
Chill tunes, btw.
@irrelevantdata3 ай бұрын
This is great! Cannot wait to try this out on my 3090.
@jonathanpadilla38883 ай бұрын
Huge
@deeplearningpartnership4 ай бұрын
Cool.
@JulianHarris4 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.
@brianboynton4104 ай бұрын
Is the language model learning to improve and if so is the policy dictated?
@tyrock50356 ай бұрын
With the right models this could be big
@jenniferh.72196 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.72196 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.72196 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
@Fircasice7 ай бұрын
That description text was written by AI.
@M96ohamed7 ай бұрын
Just subscribed! Keep up the good work mate
@d77droid7 ай бұрын
What? Man your project is awesome! How they cut you like that? Their system is not ready for you man, fukin corporats
@alexcessy7 ай бұрын
Hi Kyle, is there a way to get in touch with you?
@jnaps22137 ай бұрын
It's a shame you had so little time to present. If only AI could have accelerated that part of the process 😅😅
@omgasmurf1117 ай бұрын
Exciting! But I'd love to see a working recorded demonstration of this in action. Subbed in anticipation!
@uazik-kamazik7 ай бұрын
вот это круто!
@jonathanpadilla38888 ай бұрын
solid stuff kye swarms will take over the world
@BR-hi6yt8 ай бұрын
The stress and intonation can change the meaning of a sentence (e.g. That's your sister - has double meanings depending on stress of "That's")) - I notice there is no audio decoder that can even attempt to handle this aspect.
@Frank-pl2nz8 ай бұрын
"Promo sm" 🎊
@randotkatsenko51578 ай бұрын
About time somone did it!! Thanks. I think I MUST try this shii out ma boy :D
@zackbradshaw98399 ай бұрын
Best one yet very inspirational can't wait to implement this for my self :)
Пікірлер
Great Work
subtitles are showing but voice is not coming only music is audible
Cool
Nice
thanks!!!
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.
Hope you get better soon
thanks. get well
Intro could have been Elevenlabs api call in Sam Elliott voice. Great Idea and execution. more vids.
happy with yet again, another super channel! 👏👏👏
"Taxes and weird stuff like that" hahahah
problem is that they don't work
can you explain more? how exactly? do you have some test code
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?
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.
Yeahhhhhhhh
Why not incorporate something like Actor Model, kzread.info/dash/bejne/d4Crp8abj9OqYM4.htmlsi=B4tK4_-w2uTGXNnn , that will bring fault tolerance. Thanks Kye for make your videos more short, we dont have time to see hour long videos.
Very interesting and yeah let's do it! And, yes, will do another one coming today.
discord link expired, u need to generate the without expiry one
yeah, smh that keeps happening. Appreciate you lmk! discord.gg/P7Hb9dWx
dspy in the hishoussee!!
need to learn more about it
In general a good video. Learned how it is like when experimenting with a new architecture.
Glad you enjoyed it! stay in tune!
this random zoom effect is really annoying.
my bad. ill fix it
Bzzt. GQA was used in LLaMA-2, so it's not "in the last six months or so."
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.
Ah, I see a fellow tardigrade enthusiast (I'm only mildly joking).
Dude what happened to your amazing hair it was so original😭
I appreciate you, I took the naziretic vow and came into contact with a fallen Human. I must re-commence the holy ritual.
@@kyegomez3242 I hope you are able to complete it next time. Also thank you for the tutorial It was an interesting watch.
Thanks @kyegomez3242. Great summary description.
Impressive model, thanks for the video.
Thanks for watching!
incredibly based
Can't wait for the next videos in the series!
why is the voice so corrupted?
Your screen changes are too fast and not feeling stable and watchable.
Yeah, definitiely will take into account and optimize my future videos
TIME TO ACCELERATE 🚀
Weird... my reply is not able to be shown? Did you hide it or something?
Chill tunes, btw.
This is great! Cannot wait to try this out on my 3090.
Huge
Cool.
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.
Is the language model learning to improve and if so is the policy dictated?
With the right models this could be big
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
+ 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
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
That description text was written by AI.
Just subscribed! Keep up the good work mate
What? Man your project is awesome! How they cut you like that? Their system is not ready for you man, fukin corporats
Hi Kyle, is there a way to get in touch with you?
It's a shame you had so little time to present. If only AI could have accelerated that part of the process 😅😅
Exciting! But I'd love to see a working recorded demonstration of this in action. Subbed in anticipation!
вот это круто!
solid stuff kye swarms will take over the world
The stress and intonation can change the meaning of a sentence (e.g. That's your sister - has double meanings depending on stress of "That's")) - I notice there is no audio decoder that can even attempt to handle this aspect.
"Promo sm" 🎊
About time somone did it!! Thanks. I think I MUST try this shii out ma boy :D
Best one yet very inspirational can't wait to implement this for my self :)