LoRA - Low-rank Adaption of AI Large Language Models: LoRA and QLoRA Explained Simply

Рет қаралды 51,714

Күн бұрын

Пікірлер: 41

@IntuitiveAndExhaustive Жыл бұрын

This isn't really accurate. LoRA doesn't really make your model smaller, it makes the fine tuning process require fewer resources. As far as I understand the final model size is about the same, if not slightly bigger.

@amortalbeing Жыл бұрын

he meant during training I guess, but you are right, Lora is for fine-tuning

@viixby9481 4 ай бұрын

A better analogy I assume with the lego thing, would be that, it gives you a little handbook on how to build that specific thing with the legos. Not handpicking certain legos.

@sharathkumar8422 2 ай бұрын

Final model is slightly bigger as it has the LoRA layers added on top of the original layers unless you removed a few of the original before adding the LoRA ones. The training process however requires far less computational resources cause you're only training the newly added LoRA layers and freezing all the other model layers.

@Trinad356 Жыл бұрын

You explanation is really amazing one can easily understand without having any background knowledge, thank you very much.

@TheCradmin Жыл бұрын

This video needs more love. Thank you man, so well communicated.

@El_MA11 3 ай бұрын

That was excellent. Nice teaching skills, Wes.

@MasterBrain182 Жыл бұрын

Astonishing content Man 🚀

@lighthousesaunders7242 Жыл бұрын

Fine tunning? Stacking and transfering? Thanks for a great video.

@happyday.mjohnson Жыл бұрын

i subscribed to your channel after watching your explanation. Thank you for your clarity.

@ntesla66 Жыл бұрын

1. a large beer cask. 2. a measure of capacity, usually equal to 252 wine gallons. Otherwise well done!

@DarkDiripti 9 ай бұрын

Only watched the first lego example, and that is just plain wrong. LoRA does not make the model smaller, that analogy does not hold at all. Don't want to know what follows from such a bad analgoy.

@sheevys Жыл бұрын

Is there a speed improvement during training only or also at inference?

@Lampshadx Жыл бұрын

Training only - you may encounter latency issues during inference due to separately loading the base model and the LoRA model, but most libraries will allow you to merge them, so it would end up being equivalent to the original model.

@Lampshadx Жыл бұрын

To actually run inference and generate predictions after fine-tuning Lora, you would need to combine the original large base model weight matrices with the small updated factor matrices that Lora learns. So at inference time, you still have essentially the same enormous number of parameters as the original foundation model. The key efficiency gains are seen during the adaptation/fine-tuning process. By only updating a tiny fraction of parameters, Lora allows much quicker and cheaper adaptation compared to full fine-tuning. But once the adapted model is ready for deployment and inference, multiplying/merging those factor matrices back into the original base weights results in effectively the full set of parameters at inference time.

@moeinhasani8718 Жыл бұрын

really good video for a high-level understanding of the concept. I wish there was a little bit of math included as well, just very high level mentioning what mathematical steps are taken.

@ArunkumarMTamil 8 ай бұрын

how is Lora fine-tuning track changes from creating two decomposition matrix? How the ΔW is determined?

@seeess925 6 күн бұрын

This makes no sense. Keeps saying models over and over with no info on what it h means. I get the overall point of being limited. But no info on what it actually is it what it does.. Essentially pretty much know nothing about what lora means

@scottstout Жыл бұрын

Is it possible/reasonable to use LoRA w/ GPT-4?

@fusseldieb Жыл бұрын

Afaik GPT-4 is closed-source

@Daligliding 2 ай бұрын

What kind of tool is used making the animation?

@chyldstudios Жыл бұрын

nice explainer

@AurobindoTripathy Жыл бұрын

all that images-filling by scribbling inside the lines? How does that support your content (which in fine)?

@ceciliaedwards552 3 ай бұрын

204 Oberbrunner Valleys

@KentPage-j8u 3 ай бұрын

518 Skiles Shores

@sergeibogdanov572 Жыл бұрын

Hello, what is the name of the software you use to draw?

@loremipsum916 Ай бұрын

@FrankWilliams-r4b 3 ай бұрын

Satterfield Hill

@ChristyLynn-j1t 4 ай бұрын

458 McGlynn Circle

@AnneMorales-y2r 4 ай бұрын

Hal Crescent

@pongtrometer Жыл бұрын

I’m trying to follow your recommendation of learning python, I’m not a programmer whatsoever, so just from watching this overview, which is great by the way. Is there LoRA-esque way of learning python , so that I can be creative ,as I learn python. Just like using LoRA’s in SDXL, in combinations to create new image recipes. I hope to learn python so that I can get involved with making LoRA’s for sound design, not grounding breaking, but definitely enabling sound designers to create with new sonic colours. Any advice would be much appreciated. Thanks in advance Wes / comments community.