"okay, but I want GPT to perform 10x for my specific use case" - Here is how
Finetune Falcon 7b/40b instruct with your own data - The step by step guide about how to train falcon model for generating high quality midjourney prompt, from prep training dataset to comparing final results;
- Join Falcon 40B contest: falconllm.tii.ae/call-for-pro...
- Follow me on twitter: / jasonzhou1993
- Join my AI email list: www.ai-jason.com/
- My discord: / discord
🔗 Links
- Google colab: colab.research.google.com/dri...
- Midjourney training dataset: docs.google.com/spreadsheets/...
- RelevanceAI midjourney training dataset generator: app.relevanceai.com/notebook/...
⏱️ Timestamps
0:00 Finetune VS Knowledge base
1:50 Step1 Choose base LLM
2:30 Step2 Prep training data
4:54 Step3 Setup google colab
5:41 Step4 Load base Falcon model
6:48 Step5 Load training data
7:36 Step6 Finetune model
7:56 Step7 Save & run finetuned model
9:08 Falcon 40b
👋🏻 About Me
My name is Jason Zhou, a product designer who shares interesting AI experiments & products. Email me if you need help building AI apps! ask@ai-jason.com
#gpt #autogpt #ai #artificialintelligence #tutorial #stepbystep #openai #llm #falcon7b #finetune #largelanguagemodels #largelanguagemodel #midjourney
No clickbait, no long intro, no over-excitement. Just pure, straight-to-the-point content, with real-world examples and neatly divided sections. You are a hero
You understood that? I wish.
YES! Getting tired of those time filler AI videos, almost didn't watch this one. Now subscribed
Aaaah just like the good ol days 😅😂
@@668771knuckle down and study practice study practice, it's not that difficult 🤷🏽♂️
specific use case: filter videos for overexcitement and clickbait, then tag them
holy heck dude, you just taught us magic. This is the magic! not even the fine tuning, but the data set generation! data sources! all the pieces I have been searching for!
Thanks so much mate!! That means a lot, DM me if you get any question pls!
Literally brother you have taught us prompt engineering wizardry, there’s no other way to put it.
I’ve been generating massive data sets and manipulating in python then bringing it back to fine tune. Shits getting wild out here
@@DeepDiveNFTlol sounds like fun, what kind of general use cases do you have?
Be wary that OpenAI prohibits the use of their models to generate training data (no competing closure). It's hard to detect, obviously, but it's useful knowledge imo regardless.
Let's be honest. Who here clicked because you thought he was JIMMY YANG?
Who’s Jimmy Yang? 😂
@@shuzhu6633 the comedian in the thumbnail
jian yang
I'm not 😂
That's 😂
One thing I really like about your videos is that it always comes with really quality examples. And the examples are pretty much practical oriented. Do make the embedding video.
Thanks man, that means a lot! 😬
@@AIJasonZ Absolutely agree. Very helpful and i like the speed you go, staying on topic. Please make the embedding video! Very interested to see your take on it.
I thought the opposite, this was like watching someone assemble a nuclear reactor. I'm more confused about AI after watching this. You need to be a master programmer to properly view this video.
@@AIJasonZ +1 on make the embedding video. Really great stuff :)
Very good teaching style. I also liked that you actually went through the process ourself. Thank you very much
Honestly, I love how you don't put a clickbaity title or thumbnail, and how you explain it well but also fast.
Fantastic video once again, can’t wait for the next embedding one 😊
One of the best and most straight forward tutorials i have Seen after 5 years of ComputerScience! Keep it up now i am honna binge eatvh your other videos
Excellent video Jason. Well organised and easy to understand.
Omg this is the best one I have seen so far!!!I’m planning to train one of my own model soon!!
Really appreciate your free thought. Will try to follow you closely.
Great Video! I would love to see a video on how to create an embedded knowledge base and use it along side this fine-tuning.
most underrated channel in AI. Thank you for the effort you are putting into this.
I'm floored by your content. It is amazing 👏👏👏👏👏👏
Bloody awesome video - concise yet detailed! Looking for upcoming vids
Excellent video Jason! Step by step examples are really helpful
well done! looking forward to the embedding video too
Learning so much from you. Thank you for making this.
Man this is exactly the sort of guide I was looking for. Thank you very much.
I'm glad i found this channal! wonderful work!!
brooo....God bless you for this...gained a ton
Good work dude! This is super useful!
Your audio gradually went from studio recording to cathedral ambiant. Hey thanks for the info. Love it ♥
Great Video! Keep up the good work
Great job Jason! Very helpful!
Great concise tutorial, thanks!👍
keep the good job Jin Yang,your top follower from shanghai
honestly, I was not expecting jin yang to teach us but I'm all for it straight to the point, loved it
One of the best, to the point, goldmine of a tutorial
Awesome video! So many great resources. Demystified a lot for me. Thanks!
This is such a relevant and timely video. Thanks bud. PS I love all your silicon valley video titles
Great content! A how-to without any fluff what so ever that is easy to follow.
This is fantastic info, thanks! Subscribed.
This is just amazing! waiting for your embedding model
great video Jason - also my first ever comment on KZhead. Most practical tutorials on AI so far imo - I would be keen to see a video where you set up a vector DB and load your own data
Hah thanks, first comment means a lot to me! Will get more content :)
Much appreciated ❤️ Thanks man, this helped me alot!
Excellent tutorial on finetuning Falcon 7B
Real thanks from another Jason man, clear and concise video! As a high schooler, I'd like to create an LLM project, so I hope I can follow through after I do my research :)
Brilliant mate. Keep these coming
So useful! Thank you!
Would love to see the video on the knowledge database. Thank you for this!
Good Job Jason 👨🏽💻
Excellent lesson on Fine tuning. You are a good teacher. Thanks. Please make he next video I am now subbed.
Oh man, this is so good, i always confused about when should i finetune LLM, this makes things super clear; Also falcon 40b seem to be an awesome choice!
Good stuff Jason🤙🏻
this is gold, thank you!
All thriller no filler. Wicked vid well done sir
What an amazing to the point video! You're an amazing human being Jason. Keep doing you!
This is an amazing video that helps me make sense of the Azure Open AI playground to train my model. Love this.
Wow, what a sick video. Thanks so much!
my man great content ever, keep it up
Bro you've done something wonderful for the world with sharing this video 🎉👏 As an app dev I learned something I didn't know I needed to know
give this man a cookie, dude thank you !!!!
Yes please, waiting for knowledge base embedding video ! 🎉
This channel is going to be huge.
Great video mate! Keep up the work (Y)
Great video, dude! Thanks!
I have been spinning my wheels on a project and this video unstuck me - thanks a million!
fantastically clear
I like it. Because your video i can follow it every step. It's important for a newbine .
Astonishing content Man 👍👍👍
I appreciate this. Subscribed.
Well explained my friend👏👏
Thank you for sharing this. This will definitely help. Also epic thumbnail 😂
Absolutely loved the video mate! super focused! You inspired me for my own channel! thanks and keep it up! :))
Great video. Helped create a much tighter solution for our client.
Great content! thanks for sharing
Great job !
that was really good glad this was recommended to me
Thanks for sharing. It was helpful for understanding the fine tuning process. Can you also make a video on KnowledgeBase embedding? Thanks
really interesting! nice video! 🤗
This was super informative and I learned a lot. Great video!! Not to be rude, see this as a constructive comment, be aware of some typos you have along the video. It's not like it bothers me much or anyone, but correcting those little details add up to make your content even better! Good luck and I hope to watch more of your videos :D
Thanks for sharing!
Beyond excellent. Damn. Reminds me of Yolo and Stable diffusion in a way. I have got to read the papers sometimes and try tot write a C implementation. This is beautiful!!!!!
thanks for this amzaing videos. looking forwards to your next videos for embedded knowledge base and creating a chatbot for UI using these trained models.
Wow this is amazing, pure relevant data, tahnk you!, you got my subscription and like
Awesome! I'm totally new to fine-tuning. I'm looking forward to fine-tuning a model with thousands of private 4K images!
Looking forward to the video on embedding a knowledge base
Thank you Jin yang
you are legend tysm!
Amazing, thank you!
Hi, Thanks for the excellent video.
excellent tutporial! thank you for sharing.
really helpful and straight forward. Subbed !
Ey 😊 awesome. I created a conversational api with context management in Java. I've used gpt-4 and learnt allot. I'm hoping I can make use of this as well. Nice video.
Amazing, you are the best bro. thanks
节奏好快,剪得厉害👍
I have been looking for you for so long. Thank you so much for this. Now I can ditch open AI api key and use this for free for my usecase.
Thanks for the detail level of explanation .....
Waw that was amazing
Thanks for sharing such an amazing content! It would be great with you could also make a video about creating embeddings
Damn amazing video
Great video Jason.
Great information. I am interested in the embedding style. Would love to see a video of that.
Hi it would be really great if you could make a video showing on how to create Auto layouts. If we have the content done via these, how do we lay it out in a ppt or Adobe indesign to continue with the design work. Any thoughts or suggestions here?
This video is excellent; I appreciate your hard work. Are you considering creating a video about DemoGPT?
Greaeeeeeeeeeeettttttt ! I have been surfing through internet for last 6 months for this type of workflow tutorial and here you have just made it. Thank you so much for this. My biggest question was how to prepare my own data to finetune a specific AI model for my use case. You have explained that part very easily. Now I can start making my own chatbots. P.S I am not a tech guy .... just an accountant.😅
You should ditch your boring profession.
OMG. It's amazing. I was just wondering after a little research on the fine-tuning processes. There are actually 3 levels: Unsupervised Fine-Tuning, Instruction Fine-Tuning, RLHF. How to actually do that in coding? I couldn't really find documentations for that on different models. Some models have first two, others have just level 2. Could you provide some guide?
Thank you for the video. Is this the way to make LLM good at certain languages (spoken ones)?
🎯 Key Takeaways for quick navigation: 00:00 *🤖 Methods for GPT Usage* - Two methods discussed: fine-tuning and knowledge base. - Fine-tuning: Suitable for modifying behavior, like mimicking specific individuals. - Knowledge base: Utilized for providing accurate domain-specific data, such as legal or financial information. 01:38 *💡 Case Study: Fine-Tuning for Military Purpose* - Selection of a powerful large language model (Falcon) for fine-tuning. - Importance of quality dataset for fine-tuning model effectiveness. - Utilization of GPT to generate training data and platforms like Randomness AI for bulk processing. 05:08 *🛠️ Fine-Tuning Process* - Preparation steps for fine-tuning on Google Colab, including library installation and model loading. - Use of Low-Rank Adapters for efficient fine-tuning. - Saving and uploading the trained model to Hugging Face for sharing and further use.