Gotta admit I'm feeling kinda teary reading all the lovely comments here. Thank you everybody -- love you all!

@ksrajavel

9 ай бұрын

You just deserved it.😃

@ReligionAndMaterialismDebunked

9 ай бұрын

Second in the replies. :3

@JumpNationFilms

8 ай бұрын

You are beyond awesome, Jeremy

@Soulseeologia

8 ай бұрын

Thanks for your work and please help us keep an eye on the apostles of the emerging noosphere, like Ben Goertzel ect.

@ellevillarreal9074

8 ай бұрын

Jeremy Thank you! This has helped so much. I’ve been a FastAI builder since the early days in 2017. Youre my hero. Appreciate all of the work you’ve done in the field

Just realised Jeremys paper led to the LLM revolution. Such a humble kind man. God bless you and all your students. You are such an example to follow. An example in character, humility and intelligence.

@circleAI

8 ай бұрын

how ? which paper?

@pw7225

8 ай бұрын

@@circleAI ULMFiT

@fasteddylove-muffin6415

6 ай бұрын

@@circleAI Part of the answer is in the video's description.

@peaku8129

4 ай бұрын

Yes exactly what I was thinking, why there's so many people bragging about what they are doing and look at this guy, just helping others out.

This is probably the best invested youtube time of this year so far. What a gem. A lot of things he mentions have taken me month to figure out by my own. My new GPT-4 prompts will begin with "You are the expert Jeremy Howard..."

@ProfRvS

9 ай бұрын

This!

@shaggyfeng9110

9 ай бұрын

lol, nice

@peterdonnelly1074

9 ай бұрын

100%

@lucaleung5892

9 ай бұрын

So great.

@JarkkoHautakorpi

7 ай бұрын

Absolutely!

*Transcript Summary:* - Introduction & Basic Ideas of Language Models (00:00:00 - 00:18:05) - Limitations & Improvements of GPT-4 (00:18:05 - 00:31:28) - AI Applications in Code Writing, Data Analysis & OCR (00:31:28 - 00:38:50) - Practical Tips on Using OpenAI API (00:38:50 - 00:46:36) - Creating a Code Interpreter with Function Calling (00:46:36 - 00:51:57) - Using Local Language Models & GPU Options (00:51:57 - 00:59:33) - Fine-Tuning Models & Decoding Tokens (00:59:33 - 01:05:37) - Testing & Optimizing Models with GPTQ & Hugging Face (01:05:37 - 01:09:48) - Fine-Tuning with Llama 2 & Platypus Datasets (01:09:48 - 01:10:32) - Retrieval Augmented Generation & Information Retrieval (01:10:32 - 01:20:08) - Running a Private GPT & Fine-Tuning Models (01:20:08 - 01:22:32) - Running Models on Macs (01:26:00 - 01:27:42) - Discussing Llama.cpp & Its Cross-Platform Abilities (01:27:42 - 01:30:07) - Challenges & Opportunities in Language Models (01:30:07 - 01:31:05) Key points of interest: Function usage in GPT-4 (00:46:36), OCR application with Google Bard (00:33:59), and improving GPT-4 responses with custom instructions (00:24:36).

@qwertclyde1092

9 ай бұрын

Dope, did you do this by hand?

@4everandrew

9 ай бұрын

😅😅😅😅

@-rate6326

7 ай бұрын

I was expecting "By Tammy AI"

@uminhtetoo

3 ай бұрын

Thanks

The moment I got to know that you and Andrej weren't included in the Time's list, I realized that the people making such lists have no idea what they are doing. Loved the tutorial, thank you!

Hoping to look forward it.Ur fastai stable diffusion course was Perfect to the minute details

I found this video so useful that I felt compelled to pull my keyboard closer toward me, fix my posture, and write this comment - something I rarely do. I'm a professional data scientist hoping to push my company's GenAI agenda and this video makes me feel like I can actually do it! Thank you for so clearly encapsulating the state of LLMs. I'd learned many of these concepts before and this video is the glue that now holds it together.

very easy to know, practical! thanks Jeremy

No one can explain a topic like Jeremy👍

A true legend! So far, I have not seen a better educator than Jeremy. His approach of teaching is what all schools and universities need! I am always interested to learn more, whenever I hear Jeremy. Thank you!

@howardjeremyp

5 ай бұрын

Wow, thank you!

Truly enlightening! As a software engineer with limited math and data science knowledge, this video has been a revelation. The way Prof. Howard simplifies complex concepts is incredible, making each rewatch rewarding with new insights. Really grateful for his content that opens up the world of LLMs to a broader audience. His clear and thorough explanations are incredibly invaluable. Thanks, Prof. Howard, for demystifying this topic and helping us all learn.

@howardjeremyp

2 ай бұрын

Wow, thank you!

The best "intro" and Guide I have seen on this. Appreciate it so much that you took the time to put this together and share this with us (FOR FREE!).

By far the most useful practical guide to LLM's by length. Thank you Jeremy!

Great! It allowed me to understand how LM thinks and why.

This video landed up on my feed and out of curiosity I started watching and before I knew it had watched the entire video and taken copious amounts of notes too. One of the best videos I have ever watched!

Bravo. One of the best KZread videos I've ever watched. Concise, entertaining, and chock full of useful insights.

So many papers are being released, so it is important to have well-grounded information to understand LMs. Great delivery as always and practicable advice. Thank you.

Fabulous tour of key points. Fantastic job! Definitely going to recommend this to people wanting a gateway into llms.

I liked the video even before watching. Thanks Jeremy for your work, always learning from your content.

Jeremy you're one of the most legit AI person out there. An enormous thank you for providing this and all your content. ❤

Thanks for all you do Jeremy. I have learned so many things watching youtube as well as the PDLC tutorials. Your expanations are on point.

So comprehensive. Perhaps the best introduction I have ever seen to the topic. Thanks so much.

We do not deserve you Jeremy! YOU ARE AN AMAZING TEACHER AND HUMAN BEING! Thanks, really, for all these beautiful lectures!!

You are literally changing lives, all for free. Thank you.

I'm really grateful how much people sharing their knowledge, can't imagine learning stuff for free. this means a lot for me.

I have waited for months for a classification and evaluation from Jeremy. For me, this is by far the most comprehensive technical summary and evaluation available for someone who wants to delve deeper. It took me several weeks, if not months, to gain even a partial personal understanding of the current hype. Thank you, Jeremy, for all your good work!👍

Great video. Watched it in one sitting. It's very interesting and engaging, and does cover a lot of areas on LLM, different model, types, examples, uses cases, etc. I learned a lot and hopefully will go through the notebook in detail and adapt to my use cases. Thanks for making this.

There are hundreds of LLM tutorial coming out everyday, this is the one that I have been waiting for.

Thought provoking one code block at a time. As usual Jeremy the king

Thank you very much, Jeremy. Fascinating to see where we have come. The prose to SQL thing blew me out of the shoes. Can't wait to try this out by myself.

Very much appreciated this consolidation of the main LLM coding concepts to-date. Thank you!!

Came up in my feed. Thumbnail and title boring. By mistake I pressed play. But it was so interesting. I feel so enlightened after having been talked through this. Thanks for sharing this!

Hi Jeremy, excellent walkthrough! This is truly helpful. Please keep them coming!!

Brillant walk through. No hype. It is a real skill to explain complex topics is coherent way.

This is golden summary of the state of the LLMs, Thank You

The "wolf, goat and cabbage" riddle example is just awesome. Gotta use it to illustrate what LLMs can't do and why. Cheers for that :)

Thank you Jeremy for this introduction. It just answered many of my questions and affirmed some of my doubts about how many of the applications that use LLMs work today.

Thanks so much Jeremy, been following you since Kaggle's launch. Inspirational to see an Australian continue to kick ass as much as you have in your career.

One of the best and most educational videos I've seen on the subject. Thank you, Jeremy!

thankyou for the talk

I think the major problem is the retrieval. Would love a video just on that (best practices, best models out there etc.). Great video, came across on x and subbed immediatley.

oh man great video

Such a great article! I learned a lot from this video, such as how complicated systems can be put together using a stack of models, illustrated in the RAG to name an example. Jeremy, you are such a kind person to share this with the world.

🎯 Key Takeaways for quick navigation: 00:00 🤖 Introduction to Language Models 10:27 🧠 Neural Network Basics 16:38 🚀 The Power of GPT-4 24:53 🌐 Limitations of Language Models 25:23 💡 Language model limitations: 31:32 📊 Advanced Data Analysis: 36:18 💰 OpenAI API Pricing: 39:19 🧩 Using OpenAI Functions: 46:40 🐍 Custom Code Interpreter: 51:13 🐍 Creating a Python code interpreter 53:39 💻 Running a language model on your own computer 55:01 🏎️ Choosing a GPU for language model work 56:15 🖥️ Options for renting GPU resources 57:57 💾 GPU memory size and optimization 59:20 📚 Using Transformers from Hugging Face 01:00:06 🏆 Evaluating and selecting the right model 01:14:12 📖 Retrieval augmented generation for answering questions 01:17:10 📚 Overview of using language models for document retrieval and question answering 01:20:35 💼 Private GPT models for document retrieval 01:21:03 🎯 Fine-tuning language models for specific tasks 01:25:15 📊 Building a language model for SQL generation 01:26:36 💻 Running language models on Macs

@plebmarv9668

8 ай бұрын

gpt plugin? :D dauymn son

@erkinalp

2 ай бұрын

@@plebmarv9668 it's tammy ai, a youtube video talking points extractor

First comment on KZread here. Among all those videos on KZread, using custom instruction like what you did is literally eye opening. I thought current AI models’ limitations are limited by nature that it can’t be improved. Of course it is that you are professional in AI but things are so organized well and straightforward that I can understand and see the result right away. 😂 Gonna have to steal your instruction as well.

Kudos, such pleasurable 1 hour and 31 mins and 12 seconds.

Keep on making videos man this was highly informative and my regards to being a person who was part of forming this architecture!

This is great. I don't know how to say how much grateful I am for your video. Thank you and keep the great work!

Impressive video; I spent days learning these concepts on my own. Had this been released two months ago, it would've been a game-changer. Excellent summary.

@jackgolding4235

9 ай бұрын

Luckily i'm a few weeks behind you! Happy learning mate!

Always look forward Jeremy to explain this topic. Finally it is here. 😀

Hands down one of the best videos on LLMs on the internet.

What a great primer! Very much needed! Thanks as always Jeremy!

This is a real gem. Reminds me of the authentic, high quality training material from Andrej Karpathy. Looking forward to future similar tutorials if you decide to make them! Thank you!

I've been a student of yours for years, thank you for all you do for us. A non-optimal but correct solution to the cabbage, wolf & goat crossing works by just using incantation "think step by step" : Think step by step to solve the following tricky problem: Here is a logic puzzle. I need to carry a cabbage, a goat and a wolf across a river. I can only carry one item at a time with me in the boat. I can't leave the goat alone with the cabbage, and I can't leave the cabbage alone with the wolf. How can I get everything to the other side of the river? This classic river crossing puzzle can be solved through a series of strategic moves that ensure the safety of each item. Here's a step-by-step solution: 1. **Take the goat across first:** - You take the goat across the river and leave it on the other side. - This ensures that the goat is safe from the wolf, and the cabbage is safe from the goat. 2. **Return alone:** - You return to the original side alone to get either the cabbage or the wolf. 3. **Take the cabbage across next:** - You take the cabbage across the river. - Now, the goat is on the other side, and the cabbage is with you. 4. **Bring the goat back:** - You bring the goat back with you to the original side. - Now, the cabbage is alone on the other side, and the wolf is alone on the original side. 5. **Take the wolf across:** - You then take the wolf across the river. - Now, the wolf and the cabbage are on the other side, and you have the goat on the original side. 6. **Return alone:** - You return to the original side alone. 7. **Take the goat across one final time:** - Finally, you take the goat across the river again. - Now, all three- the goat, the cabbage, and the wolf -are safely on the other side. This way, you ensure that the goat is never left alone with the cabbage, and the cabbage is never left alone with the wolf, solving the puzzle. chat.openai.com/share/3cb73481-c45c-4108-9960-30c11615ca41

Jeremy, we need more videos on this topic! Thank you so much!

Damn I watched the whole video and didn't even realise that it was 1+ hr long! Thanks a lot for the great content!

Perfect description of Functions at 46:30!

this one presentation is worth more than all the AI discourse on internet.

This is amazing, thanks so much for recording this and sharing it 👏

Thank you for creating this amazing talk around all the basics and applications with language models, this is really helpful!

Can’t stop watching over and over again! Thank you 🙏

Thank you Jeremy!! One of the most insightful and helpful vlog posts on the inner workings of LLMs... Top marks!!!

This is remarkable. Thanks for sharing this topic for us Jemery!

Happy birthday Jeremy! Just got to the section where your bday is revealed and it is today! Thank you for all the great work :)

Great course! Hello from Almaty Google developers community!

Mr Howard never disappoints. Thanks a ton as usual Sir.

Thank you Jeremy for all of your work and for sharing such quality videos. ❤

incredible, value-packed, practical video for developers working with LLMs.

@howardjeremyp

4 ай бұрын

Glad you liked it!

I am a total beginner but u made me understand abt LM models way better than anuone else..u r such a great teacher..I pray for giving u Lord Gurus blessings dor more insight and vision for such a Humble and good Soul.😊😊

@stuartpatterson1617

8 ай бұрын

100 % agree! Blessings to you too.

Thanks for making video. Would love to see some follow up videos on use cases for fine tuning. Where does it make sense vs RAG or even just better prompts

Never miss Jeremy's lectures....

Thanks Jeremy for another wonderful lecture! Much appreciated.

I can not emphasize how incredible this video was

Such an amazing video! Thanks so much for this amazing overview of LLMs! A few suggestions for a follow-up video perhaps :) 1. How to build an LLM from scratch on a consumer grade machine (e.g. laptop with 1 good GPU or Macbook M2 Max), maybe not 1B params but e.g. 500M? 2. LORA and DPO. 3. OpenAI's updated API. 4. Agents based frameworks such as AutoGen. Thanks again - really enjoyed this video! ❤🙏

wonderful lesson as always Jeremy! I did have a laugh at the GPT-4 bit "Bad pattern recognition - thanks to Steve Newman", as if he's the sole individual responsible for that limitation

This is pure gold!!!!❤❤❤❤ I would have never found this on my own

Great content, and I love the way you structured it. Thanks :)

Awesome stuff, always like learning from your videos. Been watching since FastAI v1.

Thanks...great summary....now i know the relatiinship between neural network parameters and vector DB's

Jeremy, Congrats on the 100k subscribers. Well deserved and hopefully a catalyst to get your invaluable content more exposure.

I feel like this video was made personally just for me. Amazing.

A wealth of Information and knowledge in this video .. a master piece .. Thank you

@howardjeremyp I love the fact that you have quickstart demos and quick prototypes to illustrate each and every one of these LLM Concepts here and in general, a great breadthwise introduction to LLMs! Only wish we had this video sooner :)

I feel like I've just been pretrained with the best AI video my creator could feed me.

This is amazing and serious content. I love it. Thank you for making it available, greetings from Switzerland

Thank you for this. Couldn’t have asked for a better video.

Such an excellent video, thanks for taking up your time producing this for those very much at the start of this journey

I remember that I was rewriting some chunk of TensorFlow code with GPT4 code interpreter, and it responded that it did not access to that framework. So I input 'gpt4: "try: import torch"', respond was 'Do you want to learn Pytorch' :) All about gpt's self.awareness mechanism :)

thanks so much Jeremy. the actual method to use and make function calling on llm's was breaking my brain and I didn't understand the json schema part of it. would be wonderful if you could do a full course on the major LLM topics, Fine-tuning, RAG and Agents of course. Would be wonderful if it used mostly open source models. I haven't found a model yet that will repond reliably with function calling / agent based execution. *other than GTP-4 that is.

I was waiting for this for a long time! Thank you very much

This is absolutely fabulous. Thank you!

This is so well done and presented. Thank you.

Hey thank you for making these available for free. ❤

What a very useful and informative video -- I watched this over the course of a day and took notes -- Thanks!

@howardjeremyp

4 ай бұрын

Glad it was helpful!

Jeremy this is a gem of a video. thanks again.

Thank you for sharing your experience and knowledge, Sir.

Wonderful overview, gives me confidence to dive in!

People like you change the world!

The godfather dropping some knowledge. Thank you for keeping AI for everyone in the most responsible way.

This is an absolutely amazing video, even with no real training on AI, it was easy to follow and made complete sense. Does anyone know if you can run any of these things on the new Intel graphics cards?