"Great video with an amazing explanation! Thank you for sharing."
@aliumut337 күн бұрын
Thanks. Is it possible to make a webscraping from a given url in a column?
@Larimuss11 күн бұрын
QLORA let's me train on a 4070ti with only 12gb vram. Though I can't go over 7b model
@CatarinaReis-g3y12 күн бұрын
Thisa saved me. Thank you. Keep doing this :)
@brianbarnes74613 күн бұрын
Great explanation, best that I've seen
@rohitvishwakarma287119 күн бұрын
Gojo ?
@user-wp8yx21 күн 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.
@EntryPointAI21 күн 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-wp8yx20 күн бұрын
@@EntryPointAI this does make sense they way you put it. Thanks so much for your reply!
@MudroZvon23 күн бұрын
I used RAG while creating life coach KZfaqr 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
@619vijay25 күн бұрын
Eyes!
@NY1man1NY26 күн бұрын
Watching the first 10 minutes of this video, explains how AI works. This should be showed in schools.
@stevenwessel964126 күн бұрын
Nice logo my guy
@aashwinsharma819427 күн бұрын
Great explanation...
@CharmiTrivedi-q4n28 күн 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?
@omarpalominoscortez554129 күн бұрын
Súper... 👍 me funciono... Muchas gracias, Saludos desde Chile... 🇨🇱
@Nanichinni-wb4fjАй бұрын
This is crystal and clear❤. Awesome!
@JoanApitaАй бұрын
these is what im looking before im jumping in coding. thanks man.
@big_sock_bully3461Ай бұрын
How about QDora ?
@tituspowellАй бұрын
Very helpful - thank you!
@liberate7604Ай бұрын
Great video , Is it better to use KTO as optimizer for a binary classification?
@EntryPointAIАй бұрын
I couldn't say for sure. Binary classification is a fairly simple task, so I would start with supervised fine-tuning.
@JavierTorres-st7gtАй бұрын
How to protect a company's information with this technology?
@EntryPointAIАй бұрын
Depends on the situation and how you want to apply the company information. If you mean to prevent it leaking in chats, I would suggest cleaning your data from anything sensitive before training an LLM on it or performing an embedding.
@Ben_dover5736Ай бұрын
your have beautiful eyes
@EntryPointAIАй бұрын
Thank you!
@chrisanderson1513Ай бұрын
Saving me somr embarrassment in future work meetings. :) thanks for sharing.
@thelitbitАй бұрын
great video! referring to the paper and explaining each thing in detail really helps understand the concept to the fullest. Kudos!
@egonkirchofАй бұрын
Why do we call training a model pre-training it ?
@EntryPointAIАй 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.
@VerdonTriganceАй бұрын
Hey! Thanks for video! I never used these techniques, but what I really wants to do is to train a base or chat LLM model like llama or phi-3 on some big text (Lord of the Ring for example). But all techniques I've seen so far requires a proper dataset to be prepared, but who and how can do that? Ask all of possible questions and answer them as well? It's impossible! Don't you know how can I prepare a dataset to later train a model on?
@EntryPointAIАй бұрын
Besides including the big text in a model's pretraining, you can fine-tune on it using empty prompts, which will make the model more likely to respond in a style similar to the writing. That doesn't necessarily make it an expert on the contents. In order to answer questions about a corpus, the typical approach is to chunk it up and use RAG. I have another video on the difference between RAG and fine-tuning.
@iasplay224Ай бұрын
Thank you for the info, it was very good explained for an introduction
@guapshonen2 ай бұрын
Hi. Can entry point be integrated with voiceflow?
@EntryPointAIАй бұрын
I'm not familiar with voiceflow, so I'm not sure.
@nachiketkathoke82812 ай бұрын
really grate explanation
@pantoffelslippers2 ай бұрын
Probably one of THE BEST large language model videos I’ve seen. 😮
@LisaQiyaLi2 ай бұрын
Thanks for sharing! Curious - can you fine tune the model by providing images? For example, one use case is resumes. What if I'd like to upload resume examples that are in PDF or JPEG format?
@EntryPointAI2 ай бұрын
Multi-modal fine-tuning is definitely going to be a thing, but it's not available right now (at least, readily). For the time-being you would run an image through some OCR model to extract the text and then you could use that in a fine-tuned language model
@seanmeverett2 ай бұрын
Such a key point: probabilities, not facts. They’re quantum in nature, not binary.
@PlayOfLifeOfficial2 ай бұрын
What I learned: We are no we’re near AGi
@Sonic2kDBS2 ай бұрын
Some nice details here. Keep on.
@deepstum2 ай бұрын
Excellent explanation. Best wishes for your professional endeavors. While I rarely comment on KZfaq videos, this one deserves all the praise.
@EntryPointAI2 ай бұрын
Thank you very much!
@Ak_Seeker2 ай бұрын
Your Videos are very informative, Thank you
@Ak_Seeker2 ай бұрын
Thank you
@funkyflorion2 ай бұрын
Good summary, thanks!
@coco-ge4xg2 ай бұрын
omg I always distracted by his blue eyes😆and ignoring what his talking
@nafassaadat83262 ай бұрын
can we use QLoRA in a simple ML model like CNN for image classification ?
@RoryWilliamson2 ай бұрын
This is one of the best explanations i've seen, thanks
@BorHouse2 ай бұрын
Tomorrow I have a presentation on RAG and you are like an angel to me right now 😅
@italoaguiar2 ай бұрын
Excellent video!! Congrats and thanks! +1 subscriber ;)
@ghelmstetter-AI2 ай бұрын
Great tutorial, thanks for posting it.
@raphaelglobal3 ай бұрын
I found this useful, possibly the code needs to be improved so that the google sheet doesn't make repeated and unnecessary calls to OpenAI. At least to me it looks like calls are made every time the sheet is opened and when certain unrelated things are changed in the sheet. Overall, highly interesting.
@EntryPointAI3 ай бұрын
Thanks and agreed. It shouldn't run the code just from opening a worksheet, but it would be worth looking into more. I added a version to the code repository that uses Google Sheets' built-in caching, but it has some of its own limitations. I was thinking that going through a proxy with caching would be beneficial. Open to any ideas to reduce API calls and token usage.
@darrin.jahnel2 ай бұрын
Your videos are fantastic. Because of the amazing value you deliver on KZfaq, I discovered Entry Point and became a customer.
@EntryPointAI2 ай бұрын
Awesome! Thanks for sharing - see you on the Masterclass today 😉
@Aspect05293 ай бұрын
Fantastically done!
@ArunkumarMTamil3 ай бұрын
how is Lora fine-tuning track changes from creating two decomposition matrix?
@EntryPointAI2 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.
@ArunkumarMTamil2 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?
@EntryPointAI2 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.