Hey Sophia, thanks for such wonderful explanation of space. I am facing a issue where I am doing this all for the first time Error I'm facing is : repo does not exist I using the username same as in huggingface and using the token as password Still I'm facing issue Kudos again
@SimonMariusGalyanАй бұрын
Thank you for the fantastic overview of LlamaIndex functionalities 😊
@abdulhamidmerii5538Ай бұрын
I am halfway through reading the book myself. It is absolutely amazing. Simple and high level enough to keep you emersed when commuting, but still rich enough to learn quite a few things on the way!
@olliegoodingАй бұрын
great explanations!
@paultoensing3126Ай бұрын
How could this ever be applied to creating a RAG for a customized ChatGPT? Closer to the point, as something with a user interface that my grandmother could use? Obviously the average user simply isn’t going to run anything that has code on the page.. they’ll need a slick UI. Something like the OpenAI Custom GPT. How does that slick UI ever become integrated with what you’re doing?
@ArvindChandrashekarАй бұрын
Great video! I needed this to understand my starting point for User Activation Analysis
@CryptoMaN_RahulАй бұрын
00:03 Sebastian Raschka shares his background and work experience 02:18 Sebastian Raschka discusses his motivation for writing a Q&A book on machine learning. 06:27 Author's approach to writing the book 08:35 Using earlier layers in neural networks for embeddings depends on the data set and task 12:42 Adding layers without removing any can improve model performance 14:55 Pruning models to create more efficient smaller models 19:21 Parameter efficient model adaptation technique explained 21:22 Q Laura allows using only one GPU instead of eight for fine-tuning. 25:21 Discussion on LAMA adapters and their similarities 27:37 Machine learning foundations remain consistent with potential additions in newer editions. 31:52 Utilizing multiple GPUs for faster training 33:56 Fully sharded data parallelism in PyTorch is a combination of data and tensor parallelism. 37:45 Usage of Fabric to simplify practice in machine learning. 39:46 Discussion on fine-tuning models for specific use cases 43:53 Models may look good on the surface but lack truthfulness compared to rlhf 45:56 Europe's challenge to train an ML model with limitations 49:45 Discussion on terminology in deep learning architectures 51:52 Comparison between encoder and decoder in autoencoders 55:49 Quantization methods and their implications 57:46 Encouragement to reach out for questions and check out the book Crafted by Merlin AI.
@hectorvillafuerte8539Ай бұрын
One recommendation, instead of a list of definitions about a topic, it would be more useful explain the main topic first.Like class imbalance, what it is, explain the definition. Then the list of class imbalance concepts can be only listed and maybe you dont even need to explain each of those.
@assouliyoussef9912Ай бұрын
just brilliant , thank you
@faridr9xАй бұрын
Great video!
@amitkumarchejara6042Ай бұрын
Thank you Sophia
@wiktorwysocki5162 ай бұрын
Great you mention that those tools are not exclusive. However probably for simpler use cases one of them will be enough.
@user-jd7xl6nf7k2 ай бұрын
Great interview! I am glad to see a fellow brazilian 😁
@parekhnikunj2 ай бұрын
How do you compare streamlit vs panel?
@sjsadjf70302 ай бұрын
Amazing video but I have a question. I would be very happy if you could respond; even though it enhances the accuracy a lot, recursive retriever takes so much time. Would persisting indexes to the disk also be a solution in this case? or is there an alternative way to reduce the time? Thank you very much!! <3
@sjsadjf70302 ай бұрын
oh, when I switched the embed model to default (ada-002-v2) it is now much faster, now I understand that it is not recursion related lol :D the main question has changed to how to reduce the embedding model costs haha
@saurabhbaij2 ай бұрын
How do you research for your videos?
@junewang15552 ай бұрын
Great contents and clear messages. Thank you so much! ❤
@amitk30982 ай бұрын
Is there anyway I can implement this without langchain and llama-index? I am not in favor having my RAG solution dependent on them.
@Greatpretender11c2 ай бұрын
Hello, what is toB & toC?
@HANKTHETANKAD113 ай бұрын
Do ai Poe chat how generation image and lyric on there can you do review on ai Poe chat
@vallikatpeethamber68623 ай бұрын
Great video. One question. How do I save the model locally.
@lutfiikbalmajid3 ай бұрын
Can i train this in Mac Air M1?
@todaylive30293 ай бұрын
Can I deploy a fastapi app on it. It's basically a prediction app using deeplearning model
@user-qg7dw8fi4b3 ай бұрын
i have an api error
@ServitorSkull3 ай бұрын
You sped past the most critical part of setting up the environment. please don't do that lol
@ri3m4nn3 ай бұрын
Underrated channel
@F3363 ай бұрын
Yea his video was like a missing link explained perfectly...This one is nice too...:)
@mohsenghafari76523 ай бұрын
hi. please help me. how to create custom model from many pdfs in Persian language? tank you.
@gabecast13 ай бұрын
What I love the most is the kitten on the lower right of the video :)
@xspydazx3 ай бұрын
Also thanks ! As after watching this video I also re-watch kaparthy and recreated everything and it worked ok for a text generation model .
@xspydazx3 ай бұрын
Sorry but how to save the final model produced for deployment ? .. then how to fine tune this model for a downstream task such as question and answer ?
@iSanyasiBaba3 ай бұрын
Thank you, Sophia.
@usama579263 ай бұрын
Thank you
@eyzup3 ай бұрын
Contagious enthusiasm from a frontline pro
@imai_official3 ай бұрын
--start is promt? also Sophia please tell, will it work for other language?
@venkatreddy-px8fm4 ай бұрын
Please, can you let me know if you connected your GPU to MAC M1 laptop or other source ?
@user-bw1py8mn6k4 ай бұрын
Thank you Sophia, you really explained everything in clear way. How many hours(may be days, already) lost trying to find what you have explained! (sigh)👏
@user-bw1py8mn6k4 ай бұрын
thank you very much, sister!
@sonkyung32974 ай бұрын
a tutorial of a tutorial -- lol -- much thanks!! 🙏
@peacetothehumanity55584 ай бұрын
Hi, I just discovered your channel, love the content, i was wondering what would you use to make an LLM write code like you would do it, would use the codebase/context aware method or the training method, if so what tools and LLMs would be the best, if you make a video about this. Thank you
@soumyaghosh33364 ай бұрын
Awesome explanation Sophia !!
@TheLazyEngineer4 ай бұрын
@13:00 what statistical test is used to calculate the p value?
@zeldacamila4 ай бұрын
Hey, thank u for this nice video. Can you please explain me how to set secret variables?
@jerryoverton70374 ай бұрын
Really useful stuff! Thanks for making this video.
@bjaburg4 ай бұрын
Excellent. Thanks so much. Question: is using ConversationalRetrievalChain more expensive (tokenwise)?
@sardorabdirayimov5 ай бұрын
Proofed it with Python: kzbin.info/www/bejne/q3bNe5KOeq5-jJo Thanks fir sharing!
@sardorabdirayimov5 ай бұрын
Great explanation!
@sardorabdirayimov5 ай бұрын
Watched 3 times + read the reference! Great simple explanation!