Thanks! This is among the clearest and most concise explanations of LoRA and QLoRA. Really great job.

I have been using thiese techniques for a while now without having a good understanding of each of the prameters. Thanks for giving a good overview of both the techniques and the papers

I love this video man. watched it at least 3 times and came back to it before a job interview also. Please do more tutorials /explanations !

I loved the explanation! Please make more such videos!

It was incredible and very helpful video. Thank you man!

great video! referring to the paper and explaining each thing in detail really helps understand the concept to the fullest. Kudos!

Good explanation of LoRA and QLoRA

This is really well presented

Loved the contnt! Simply explained no BS.

I've watched a couple other of your videos - you're a very good teacher - thanks for doing this.

This is really helpful, Thank you!!

great video, i think the best explanation i've seen on this, i'm also really confused about why they picked the rank and alpha that they did.

Some nice details here. Keep on.

🎯 Key Takeaways for quick navigation: 00:00 🤖 *Introduction to Low Rank Adaptation (LoRA) and QLoRA* - LoRA is a parameter-efficient fine-tuning method for large language models. - Explains the need for efficient fine-tuning in the training process of large language models. 02:29 🛡️ *Challenges of Full Parameter Fine-Tuning* - Full parameter fine-tuning updates all model weights, requiring massive memory. - Limits fine-tuning to very large GPUs or GPU clusters due to memory constraints. 04:19 💼 *How LoRA Solves the Memory Problem* - LoRA tracks changes to model weights instead of directly updating all parameters. - It uses rank-one matrices to efficiently calculate weight changes. 06:11 🎯 *Choosing the Right Rank for LoRA* - Rank determines the precision of the final output table in LoRA fine-tuning. - For most tasks, rank can be set lower without sacrificing performance. 08:12 🔍 *Introduction to Quantized LoRA (QLoRA)* - QLoRA is a quantized version of LoRA that reduces model size without losing precision. - It exploits the normal distribution of parameters to achieve compression and recovery. 10:46 📈 *Hyperparameters in LoRA and QLoRA* - Discusses hyperparameters like rank, alpha, and dropout in LoRA and QLoRA. - The importance of training all layers and the relationship between alpha and rank. 13:30 🧩 *Fine-Tuning with LoRA and QLoRA in Practice* - Emphasizes the need to experiment with hyperparameters based on your specific data. - Highlights the ease of using LoRA with integrations like Replicate and Gradient.

This video deserves more likes

Great video!

really grate explanation

Dude u look like the lich king with those blue eyes

@practicemail3227

2 ай бұрын

True. 😅 He should be in acting career ig.

@EntryPointAI

2 ай бұрын

You mean Lich King looks like me I think 🤪

Saving me somr embarrassment in future work meetings. :) thanks for sharing.

This was wonderfully educational and very easy to follow. That either it makes you a great educator or me an idiot :P Regardless, thank you.

@EntryPointAI

6 ай бұрын

let's both say it's the former and call it good! 🤣

wow I'm noobie in this field n I been testing fine-tunen my own chatbot with differents techniques, n I found a lot of stuff, but It's not commonly find a some explanation to understand the main reason of the use of it, ty a lot < 3

Awesome explanation! Which camera you use?

@EntryPointAI

3 ай бұрын

Thanks, it’s a Canon 6d Mk II

can we use QLoRA in a simple ML model like CNN for image classification ?

Bright eyes

Nice video, congrats! LoRA is about fine-tuning, but is it possible to use it to compress the original matrices to speed up inference? I mean decompose the original model's original weight matrices to products of low-rank matrices to reduce the number of weights.

@rishiktiwari

2 ай бұрын

I think you mean distillation with quantisation?

@EntryPointAI

2 ай бұрын

Seems worth looking into, but I couldn't give you a definitive answer on what the pros/cons would be. Intuitively I would expect it could reduce the memory footprint but that it wouldn't be any faster.

@TheBojda

2 ай бұрын

@@rishiktiwari Ty. I learned something new. :) If I understand well, this is a form of distillation.

@rishiktiwari

2 ай бұрын

​@@TheBojdaCheers mate! Yes, in distillation there is student-teacher configuration and the student tries to be like teacher with less parameters (aka. weights). This can also be combined with quantisation to reduce memory footprint.

In LoRA, Wupdated = Wo + BA, where B and A are decomposed matrices with low ranks, so i wanted to ask you that what does the parameters of B and A represent like are they both the parameters of pre trained model, or both are the parameters of target dataset, or else one (B) represents pre-trained model parameters and the other (A) represents target dataset parameters, please answer as soon as possible

@EntryPointAI

Ай бұрын

Wo would be the original model parameters. A and B multiplied together represent the changes to the original parameters learned from your fine-tuning. So together they represent the difference between your final fine-tuned model parameters and the original model parameters. Individually A and B don't represent anything, they are just intermediate stores of data that save memory.

@kunalnikam9112

Ай бұрын

@@EntryPointAI got it!! Thank you

LoRa (Long Range) is a physical proprietary radio communication technique that uses a spread spectrum modulation technique derived from chirp spread spectrum. It's a low powered wireless platform that has become the de facto wireless platform of Internet of Things (IoT). Get your own acronym! 😂

@EntryPointAI

2 ай бұрын

Fair - didn’t create it, just explaining it 😂

how is Lora fine-tuning track changes from creating two decomposition matrix?

@EntryPointAI

Ай бұрын

The matrices are multiplied together and the result is the changes to the LLM's weights. It should be explained clearly in the video, it may help to rewatch.

@ArunkumarMTamil

Ай бұрын

@EntryPointAI My understanding: Orignal weight = 10 * 10 to form a two decomposed matrices A and B let's take the rank as 1 so, The A is 10 * 1 and B is 1 * 10 total trainable parameters is A + B = 20 In Lora even without any dataset training if we simply add the A and B matrices with original matric we can improve the accuracy slighty And if we use custom dataset in Lora the custom dataset matrices will captured by A and B matrices Am I right @EntryPointAI?

@EntryPointAI

Ай бұрын

@@ArunkumarMTamil Trainable parameters math looks right. But these decomposed matrices will be initialized as all zeroes so adding them without any custom training dataset will have no effect.

Why do we call training a model pre-training it ?

@EntryPointAI

15 күн бұрын

Not sure if that's a rhetorical question, but I'll give it a go. You can call it just "training," but that might imply that it's ready to do something useful when you're done. If you call it "pre-training" it implies that you'll train it more afterward, which is generally true. So it may be useful in being a little more specific.

Oh my god your eyes 😍😍😍😍everybody deserves hot teacher😂❤

Are you trying to hypnotize us with those eyes 😜

I wish people would actually share links to papers they reference...

@EntryPointAI

5 ай бұрын

LoRA: arxiv.org/abs/2106.09685 QLoRA: arxiv.org/abs/2305.14314 Click "Download PDF" in top right to view the actual papers.

@DrJaneLuciferian

5 ай бұрын

@@EntryPointAI Thank you, that's kind. I did already go look it up. Sorry I was frustrated. It's very common for people to forget to putlikes to papers in show note :^)

Ahh very interesting thank you! *goes to fine tune pictures of anime girls*

your have beautiful eyes

omg I always distracted by his blue eyes😆and ignoring what his talking