Пікірлер
@abdelrahmanmagdi6767
@abdelrahmanmagdi6767 19 сағат бұрын
just perfect explaination !
@BijouBakson
@BijouBakson 6 күн бұрын
Thank you
@joshuatettey7771
@joshuatettey7771 14 күн бұрын
Great video
@omarsherif88
@omarsherif88 15 күн бұрын
Very useful, thank you!
@luckelly2378
@luckelly2378 18 күн бұрын
Such an incredibly clear presentation! Thank you
@hoyinleunghk
@hoyinleunghk 21 күн бұрын
Excellent explanation thank a lot!
@pamelamadingdong
@pamelamadingdong Ай бұрын
Fact that you gave a concrete examples really helped me go through this! Thank you for the great video
@web3namesai
@web3namesai Ай бұрын
Great insights on AI techniques! With Web3NS, you can fine-tune AI agents on YourName.Web3, combining RAG and prompts to create smarter, decentralized responses tailored to your needs. 🚀
@gayathrisaranath666
@gayathrisaranath666 Ай бұрын
Thanks for this clear explanation about the topic! Your way of relating back to research papers is very interesting and helpful!
@dickerjunge2119
@dickerjunge2119 Ай бұрын
I think there is a mistake your explanation. It uses higher precision while finetuning, but it does **not** recover "back to normal". It stays in the quantized dataformat.
@princekhunt1
@princekhunt1 2 ай бұрын
Nice
@rameshpjain
@rameshpjain 2 ай бұрын
Such a simple way to explain. Thank you.
@AbdoGhazala-y5p
@AbdoGhazala-y5p 2 ай бұрын
can you share the presentation document
@pratikmandlecha6672
@pratikmandlecha6672 2 ай бұрын
Loved the explanation. Despite knowing these terms well, I was curious to see how it would be explained and I am glad that I watched this video
@jb-mk5ln
@jb-mk5ln 3 ай бұрын
Incredibly high quality content, thank you.
@Gayatritravelandfitnessvlogs
@Gayatritravelandfitnessvlogs 3 ай бұрын
Thanks a ton!
@priscillaleapman2367
@priscillaleapman2367 3 ай бұрын
Martin Shirley Jackson Kenneth Allen Mary
@chrisder1814
@chrisder1814 3 ай бұрын
hello can you help me
@kritarthlohomi3305
@kritarthlohomi3305 3 ай бұрын
bradley cooper in limitless tf
@MarshallRoy-h9e
@MarshallRoy-h9e 3 ай бұрын
Melisa Branch
@mandrakexTV
@mandrakexTV 3 ай бұрын
This is the best detailed video and nicest explanation on youtube right now. I do think your channel will grow because you are doing an EXCELENT job. Thank you man.
@TheDinosaurDemocracy
@TheDinosaurDemocracy 3 ай бұрын
This is amazing! How do you deal with request limits? I'm set to 3RPM for all models, so I'm unable to drag and drop this into a sheet as it will only do 3 at a time.
@EntryPointAI
@EntryPointAI 3 ай бұрын
Good question. I don't have a good answer right now except to find yourself a higher limit :) 3rpm is really really low and you should be able to find even a free service or wrapper that offers more. Check out Groq or Together.ai
@bobrarity
@bobrarity 3 ай бұрын
damn bro thanks, I'm new to fine-tuning, needed to migrate my rag model to the ragtag model, and your video was very clear and helped me a lot 😊
@EntryPointAI
@EntryPointAI 3 ай бұрын
Sick, glad to hear it!
@tgzhu3258
@tgzhu3258 3 ай бұрын
so good!!
@NathanielMaymon
@NathanielMaymon 3 ай бұрын
What's the name of the paper you referenced in the video?
@EntryPointAI
@EntryPointAI 3 ай бұрын
Here's LoRA: arxiv.org/abs/2106.09685 and QLoRA: arxiv.org/abs/2305.14314
@adriadebatlle5755
@adriadebatlle5755 3 ай бұрын
It may be a stupid qüestion, is it possible to download the fine tunned model at entrypoint? Thankyou. Grate video! I came trying to see if it is possible to download it but I understood more about the website and it's grate.
@EntryPointAI
@EntryPointAI 3 ай бұрын
It depends on what service you use to fine-tune, the proprietary ones like OpenAI don't let you download it. Others like Replicate do.
@AryanKumarBaghel-cp1jv
@AryanKumarBaghel-cp1jv 3 ай бұрын
Perfect differentiations. Thankyou
@partymarty1856
@partymarty1856 4 ай бұрын
blud why your eyes like that
@someguyO2W
@someguyO2W 4 ай бұрын
Best video I've seen on the topic. Thank you!
@andrepemmelaar8728
@andrepemmelaar8728 4 ай бұрын
Very useful! Marvelous clear explanation with the right amount of detail about a subject that’s worth understanding
@routergods
@routergods 4 ай бұрын
I've been binge watching LLM-related videos and most have been regurgitation of docs or (probably) GPT/AI generated fluff pieces. This video clearly explained several concepts that I was trying to wrap my head around. Great job!
@someguyO2W
@someguyO2W 4 ай бұрын
Similar comments. He actually explained it properly.
@UfcFan-d6s
@UfcFan-d6s 4 ай бұрын
Amazing for struggling students. Love from Korea😂
@thndesmondsaid
@thndesmondsaid 4 ай бұрын
Thank you!
@archchana7756
@archchana7756 4 ай бұрын
very well explained, thanks :)
4 ай бұрын
Awesome. Thanks
@yesid3777
@yesid3777 4 ай бұрын
Thanks!, an amazing explanation!, +1 Sub.
@mohammedAlbared
@mohammedAlbared 4 ай бұрын
"Great video with an amazing explanation! Thank you for sharing."
@aliumut33
@aliumut33 4 ай бұрын
Thanks. Is it possible to make a webscraping from a given url in a column?
@EntryPointAI
@EntryPointAI 4 ай бұрын
This is a task better suited for another tool. I'd check out apify.com/
@Larimuss
@Larimuss 5 ай бұрын
QLORA let's me train on a 4070ti with only 12gb vram. Though I can't go over 7b model
@CatarinaReis-g3y
@CatarinaReis-g3y 5 ай бұрын
Thisa saved me. Thank you. Keep doing this :)
@brianbarnes746
@brianbarnes746 5 ай бұрын
Great explanation, best that I've seen
@rohitvishwakarma2871
@rohitvishwakarma2871 5 ай бұрын
Gojo ?
@user-wp8yx
@user-wp8yx 5 ай бұрын
I'm pulling for another vid on alpha. Oobabooga suggests twice your rank. The Chinese alpaca lora people use a rank 8 with alpha 32 and I guess it worked. I've tried high alphas that make the model kinda crazy. Need guidence.
@EntryPointAI
@EntryPointAI 5 ай бұрын
When in doubt, set alpha = rank for the effective scale factor to be 1. There are better ways to have a larger impact on training than bluntly multiplying the change in weights, like improving your dataset or dialing in the learning rate.
@user-wp8yx
@user-wp8yx 5 ай бұрын
@@EntryPointAI this does make sense they way you put it. Thanks so much for your reply!
@MudroZvon
@MudroZvon 5 ай бұрын
I used RAG while creating life coach KZbinr AI character in Telegram. I prepared a lot of AI processed data of him, with fine-grained segments. The prompt itself is also crafted according to the latest Claude prompt discovery. the most amazing AI experience for me yet - JulienHimselfBot
@619vijay
@619vijay 5 ай бұрын
Eyes!
@NY1man1NY
@NY1man1NY 5 ай бұрын
Watching the first 10 minutes of this video, explains how AI works. This should be showed in schools.
@stevenwessel9641
@stevenwessel9641 5 ай бұрын
Nice logo my guy
@aashwinsharma8194
@aashwinsharma8194 5 ай бұрын
Great explanation...
@CharmiTrivedi-q4n
@CharmiTrivedi-q4n 5 ай бұрын
Hello, thank you for a great video. I am trying to integrate it with the app script but i keep getting error on var Response line in saying invalid user content. Is there any alternative to that?
@omarpalominoscortez5541
@omarpalominoscortez5541 5 ай бұрын
Súper... 👍 me funciono... Muchas gracias, Saludos desde Chile... 🇨🇱