"okay, but I want Llama 3 for my specific use case" - Here's how
Рет қаралды 112,915
Күн бұрынIf you want a personalized AI strategy to future-proof yourself and your business, join my community: www.skool.com/new-society
Follow me on Twitter - x.com/DavidOndrej1
Please Subscribe.
Major credit to @engineerprompt who beautifully explained the entire Google Colab.
Title heavily inspired by: @AIJasonZ
My Google Colab: colab.research.google.com/dri...
Unsloth GitHub: github.com/unslothai/unsloth?...
Dataset: huggingface.co/datasets/yahma...
@DavidOndrej Ай бұрын
If you want a personalized AI strategy to future-proof yourself and your business, join my community: www.skool.com/new-society
@ThisIsSimonBorec Ай бұрын
I highly recommend it, the community is fabulous!
@PreparelikeJoseph 10 күн бұрын
Ive been a wordpress developer for the past 20 years and then became the lead search engine optimization manager for an agency, I see a lot of things in AI that are replacing the need for me, I’d like to learn a new skill set in AI that makes me irreplaceable. Maybe I can run an ai automation agency
@vishalsaichindepalli2798 Ай бұрын
It would be great if you could make a video on how to create datasets for fine tuning using LLM's/Agents!
@d.d.z. 23 күн бұрын
It can be so helpful!
@AndreSilva-oy5kv 18 күн бұрын
each problem you will need to adjust your dataset, this is why data engineers and data scientists work together. If i were a beginner i would start reading public IA notebooks in kaggle, in order to be able to create my own dataset.
@RUSHIKESHTHORAT-sb6rv 4 күн бұрын
did u find any way
@christopheboucher127 Ай бұрын
yes dataset made by agents ! Thx for all your content !
@Matthew-tg4uk 26 күн бұрын
vicious circle. give llm a little data and say simulate. llm uses trained data to simulate. user takes simulated data and does the same in another llm. very little new data has been added to the system.
@AlphaCrucis Ай бұрын
This is the kind of content that I've been wanting to see that I haven't been able to find in an easily digestible form.
@alvinjamur1 Ай бұрын
why are some here trashing david ondrej? he is imparting knowledge in an easy to understand way for peeps that do not know. i wrote my first neural net from scratch in 1993 and i have been an ML practitioner since then. i can tell u that info back then was hard to come by. be grateful that u have easy access to it. if u dont like it better to move along rather than disperse caustic.
@laimi7 Ай бұрын
Thank you for this video. The topic of fine-tuning was very interesting to me.
@jonathanholmes9219 Ай бұрын
Yes please. Team of Agents to create a fine tuning data set from your proprietary data.
@thiago.nobrega Ай бұрын
Keep up the amazing work bro. You provide us valuable knowledge.
@flavorbot Ай бұрын
love the videos thanks a lot for taking the time to put them out
@sethjchandler Ай бұрын
I have seen a lot of videos on fine-tuning and read a lot, and I have to say this is one of the most lucid, explanations. By making it very concrete and showing the code and, importantly, the training data you make very clear what is going on in fine tuning great job!
@gonzalodijoux5953 28 күн бұрын
hello, do you know if it's possible to fine tune with ebook pdf on a specific domain (financial, medical...) ?
@dennisking8281 Ай бұрын
Yes, please make a video on how to create the datasets for fine tuning AI - and Thanks for all you do.
@NB-qq8wo Ай бұрын
LOVE these empowering videos, thanks for sharing 🙏
@Chris-zc9bp Ай бұрын
TY I finally trained my first model. Here's another vote for the how to create the fine tuning using LLM agents.
@jayhu6075 Ай бұрын
This is a very useful topic, in the future we can train our datasets to specifically use them for different applications, particularly in healthcare or other institutions, benefiting people. Hopefully, a next topic will be about how to create your own datasets. Thanks for the explanation
@kylearnold9647 Ай бұрын
You're putting out some great content
@DrKnowitallKnows Ай бұрын
Hey I could be wrong but I believe you'll have better luck fine tuning with a less quantized version of the model. At least 8 or 16bit would be preferable to 4. I'm not an expert on quantized models, but you lose a lot of resolution when you quantize that much and that likely makes it more challenging for the LoRA to train. Definitely correct me if I'm wrong, folks, but I think this is the case.
@AlphaCrucis Ай бұрын
Nice to see you here!
@isaacnaughton5206 5 күн бұрын
Yes, this is consistent with the programming adage 'optimize last'. The trade off is speed for accuracy, but refined-model accuracy will be more important in the longer term than the speed of the refinement process itself.
@VaibhavPatil-rx7pc Ай бұрын
Excellent information ❤
@isaacnaughton5206 5 күн бұрын
This is a great video David, you've got yourself a new subscriber. I've been looking for some guidance on this for a while. Don't sweat on not being a complete expert on the topic; you don't need to be 100% across every aspect of a topic to point someone in the right direction. People can fill in the gaps as required.
@jees__antony Ай бұрын
Great work... Thanks for the tutorial ❤❤❤
@zeynelacikgoez Ай бұрын
It would be an interesting topic for a video on how to use agents to generate data for fine-tuning.
@darkesco Ай бұрын
Very useful information!
@user-fe4qc7ot5d Ай бұрын
Where is fine tuning models stored and how can I find and download it for use?
@carnageasada5350 Ай бұрын
Please do make a video on creating datasets, both with and without the use of agents!
@kamruzzamanuzzal3764 Ай бұрын
any way to input images as well to fine tune on image and text at the same time?
@MathiasKinninkpo 6 күн бұрын
Thanks for the contents. How can we made a dataset by agents, for simulating an interview for example ?
@zippytechnologies Ай бұрын
If there a way to generate the dataset input output data from contextual data like emails and q&a from website forums?
@glorixx5974 27 күн бұрын
Great vid, it would be really awesome if you could make a video on how to make data sets for fine tuning! That would help a lot
@UnSingeEnivre Ай бұрын
I would love to see a dataset fine tuning tutorial!
@Jonathan-et4df Ай бұрын
please make a video on how to create datasets!
@kamipls6790 Ай бұрын
Hey Ondrej! I think this might be a stretch of the topic, but is it possible to use an llm like llama 3 and fine tune it to respond in another language or would it be necessary to train an llm from scratch for this?
@icesteel5855 Ай бұрын
As I am , i need to know this
@rougeseventeen 18 күн бұрын
thanks for the tutorial!!
@user-xk6rg7nh8y Ай бұрын
Thanks alot !!! it is really helpful :)
@user-ef4df8xp8p Ай бұрын
Thank you...
@joseeduardobolisfortes Ай бұрын
This video is exactly what I was looking for. Thank you. Now, I wish to know which hardware configuration I will need to install and use Llama 3 models locally in my own machine. Can you help me?
@humanbeingmusic Ай бұрын
can you offer any advise about importing the ggufs into ollama, mine just spit out gibberish, I presume it has something to do with the modelcard but no idea
@agenticmark 20 күн бұрын
your right headphone will be over your eye soon ;D Thanks for the great content David!
@gnoppixlinux Ай бұрын
love the 3 primary colors at 10:12 :)
@SpicyMelonYT 28 күн бұрын
Is the trained model able to be used with "ollama run trained_model_name"? Do I have to download it directly and put it some where for that to work? I currently have a python program setup that uses the ollama module and runs llama3. But I would like to use a fine tuned model instead as I am trying to make a Jarvis like personal assistant!
@gileneusz Ай бұрын
10:29 that would be great tbh, using agents to make dataset to finetune the model is just like inception, you can also make agents to prepare dataset for other agents to create dataset to finetune the model (inception level 2) or make agents to prepare dataset for agents to prepare dataset for finetuning the model which will be used to prepare dataset for agents to prepare dataset............
@DrumAndSpaces Ай бұрын
perfect timing i was just thinking about having multiple llama 3 versions fine tuned for specific coding projects instead of a broad coding language base. is this just a waste of time and im better off having a general coding version instead? i was considering having a few fine tuned models to imitate a development team with crew.
@jackderrida Ай бұрын
3:37 He is 100% correct that already fine-tuned LLMs like GPT, Claude, and even Gemini 1.5 Pro with 1m+ context, are freaking awful at trying to emulate writing styles. Worst part about ChatGPT for this purpose is that no matter how much you tell it not to, it's filled with clauses like "On the other hand,", "Finally, ", or "As a consequence" and I'll explain to it again all the reasons those phrases don't belong in a rap song.
@Balajik7-qh1pq 27 күн бұрын
awesome David
@belu6914 Ай бұрын
Did anyone get the example running? The copied notbook results in an error when starting the training. I already fixed the missing comma and set the max_steps to 60.
@anomiedesign5030 16 күн бұрын
@David what do you suggest if you want to create javascript? and how do i train it?
@jimmysrandomness 6 күн бұрын
is there a unrestricted dalle e generator? or a something simular like dalle. i like it but the restrictions around it is just crazy now these days.
@DavidOndrej 6 күн бұрын
of course, there are plenty of unrestricted SDXL models
@jimmysrandomness 6 күн бұрын
@@DavidOndrej What I'm looking for is an unregistered Dalle model The reason for it is that Dalle can convert simple text into extended prompts, unlike many other engines like sdxl
@Will_669 28 күн бұрын
what's the dataset like if train for conversations? for example: in a conversation, we have one instruction, multi inputs, and multi outputs
@JenuelDev 3 күн бұрын
your a savior
@farazfitness 8 күн бұрын
Need help with this can you do a video how to use it on gpt4all after fine tuning I'm unable to do that. Also amazing video thank you soo much
@PaulFishwick Ай бұрын
This seems like a lot of work in forming the data prep rather than the RAG approach (eg. custom GPTs) where you embed N documents to “fine tune”. Thoughts on each approach?
@wetcel1236 Ай бұрын
Hey David, thanx for this awesome served topic! Exactly what I need to get through this week 😅
@yongxing1848 Ай бұрын
when are you going to make datasets for fine-tuning, I have currently data in mysql that I need to extract and create the datasets for fine-tuning llama.
@sourabhiitian Ай бұрын
hi i have a question, what if i want to use my dataset json file into the cell instead of huggingface alpaca json. Can you give the part of the input code
@user-ff3vb2xt4m 11 күн бұрын
What is the python version used in the above colab code
@nasiksami2351 Ай бұрын
Hey David, great video and great explanation. Please make a tutorial on how to generate dataset using LLM. For my use case, I have a classification problem and the class imbalance is severe. for the minority classes, I want to generate more meaningful samples using LLM and then build an LLM model to do text classification on the dataset. Any suggestion on achieving this would be great!
@RemekKinas Ай бұрын
I am looking for tutorial how to generate dataset using Agents. There is no such tutorial (or I am not able to find it). It would be great to generate chat format (conversation) dataset as a response of task. So as an input you have list of task, question and then agents generate conversation to this topic.
@christiansroy Ай бұрын
You can definitely fine-tune ChatGPT 3.5 and you can also ask open AI to invite you to their private waitlist to be able to fine tune GPT 4. So it is definitely possible.
@siema32 28 күн бұрын
Actually GPT-4 can be fine-tuned by the user, it's done within the openai API and of course used by it's API later on. It obviously has downsides, like the model is still invoked on the OpenAI servers and they are collecting all the data which goes through it (no privacy), but it is possible :)
@tekipeps Ай бұрын
Nice, how to deploy the saved model?
@stanisd Ай бұрын
open AI has its own API for fine-tuning
@user-vt1qs1ge7m 8 күн бұрын
do we have to pass a csv an an input data or json ?
@GreenStorm01 Ай бұрын
How about Fine-Tuning vs. RAG in those specific things?
@giseiitb 9 күн бұрын
I didn't understand, where you gave your dataset to fine-tune on?
@nimesh.akalanka Ай бұрын
Is there any free method to fine tune an large language model locall. I have a small workstation with 128GB DDR4 memory, Nvidia RTX A1000 X2 SLI VGA, AMD Threadripper process. I tried AutoTune-Advanced and LLaMA-Factory. They both failed on me. Autotrain say I dont have enough VRAM. LLaMA-Factory say I dont have CUDA. Please help me.
@andrelvcoelho Ай бұрын
Yeah, it would be nice if you could set up a video showing how to automatically generate datasets for fine-tuning LLMs… Tks
@richierosewall3035 Ай бұрын
Hey what about phi-3..?
@josephtilly258 Ай бұрын
Are local LLM really that local or just free ? Because I'm not really running it on my computer, more of a cloud base free and flexible llm ?
@theobgshow Ай бұрын
Yea they are. You can run ollama on your computer then pull down a model, such as llama3, Mistral or Dolphin and run everything, completely locally
@AlejandroCastillo9 Ай бұрын
I want to Create a Lama 3 legal Assistent. I would be happy in you can Show a data prep example
@RUSHIKESHTHORAT-sb6rv 4 күн бұрын
how do i make the dataset
@trueindian03 Ай бұрын
How to train a data set which is not in the form of instructions, input, output format, lets say I want to train the model using the data from a pdf, or any other means, how can we do that, please suggest some ideas. Thanks in advance.
@AndreSilva-oy5kv 18 күн бұрын
i've been seen people using llava model to train models like that
@vickihenderson8468 2 күн бұрын
Its is possible to create something local with llama to run on a raspberry pi and have it check spelling and grammar and rephrase things like Grammarly
@Because_Reasons 9 күн бұрын
I'm finding the data-set stuff very confusing. What if I want to create a data-set that's just my writing? I want the model to emulate my writing perfectly. I don't have question/answer pairs.
@ScROnZjara Ай бұрын
More content with lama!!! 🙏❤️
@CodingScot Ай бұрын
Do you ever sleep? Wow this is amazing 🎉👏
@strategy419 29 күн бұрын
did you try finetuning gpt3.5 on the playground?
@shaigrustamov5115 Ай бұрын
it's a good video, thanks. But there are a lot of videos about fine tuning. It would be perfect if you would create a video on how to create own data sets for fine tuning. 👍
@thedatascientist-lg4ls Ай бұрын
Yeah, a video on agents for finetuning datasets with a fine tuned LLMs, and used by agents for a real world application.
@harristengku7153 Ай бұрын
Oh wow you managed to fix the fine-tuning issue? Its been a headache for the entire open source rn, because Llama 3 trained their models differently so every fine tune would end up way worse than the original base model.
@DavidOndrej Ай бұрын
If you watch the video, you will see that I openly admit that I am not an expert when it comes to fine-tuning. In fact, making this video definitely was outside of my comfort zone.
@harristengku7153 Ай бұрын
@@DavidOndrejay respect man. In fact I think you should include more fine tuning to your videos in the future. You can’t run away from fine tuning if you want A.I to move to commercial use. Llama 3 is probably the only exception in the industry rn that has everyone stumped
@alma4355 Ай бұрын
I'm a subscriber, please make the making dataset video
@adilzahir9921 Ай бұрын
I want to use that for my work , i want to use it to find the best strategy for debts recoverts and to choose the debtors who will pay mostly and who don't ,how i should proceed ? Thanks
@ASchnacky Ай бұрын
I had same idea
@adilzahir9921 Ай бұрын
@@ASchnacky y'a that would be great if we can do that without coding ,good luck
@eldinmujovic8705 Ай бұрын
Can I do this in any language?
@samfisher92sc Ай бұрын
Please bro make a video for create datasets
@brianmorin5547 Ай бұрын
If pushing to hugging face, no config.json so won’t work
@brutely9718 Ай бұрын
NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs:
@zoranProCode Ай бұрын
Lava FRI?
@RUSHIKESHTHORAT-sb6rv 4 күн бұрын
please make make video dataset bro plzzzzzzzzzz
@Corteum Ай бұрын
What's an example of what you or someone else has created with this?
@MrAtomUniverse Ай бұрын
its no longer april T.T
@jackgaleras Ай бұрын
Fine tune or RAG
@kingKai2022 28 күн бұрын
colab doesnt work....
@RedShipsofSpainAgain Ай бұрын
This guy's community is $77/month. There's 510 members. $77/month * 12 months = $924/yr. $924/yr * 510 members = $471,240/yr. So this guy's subscription is grossing nearly half a million USD annually.
@DavidOndrej Ай бұрын
I wish… not everyone joined at 77
@equious8413 12 күн бұрын
I actually hate that everyone is using collab 😤
@mateuslima788 5 күн бұрын
Exactly! Like why? I have my own GPU. why don't tutorials teach how to do it on my own PC?
@pythonholic Ай бұрын
I really don't see the benefit in using an AI agent. I've tried to understand its purpose, but it seems like another way of avoiding using GPT and similar models. Can you give us a real example? Perhaps even instances of freelance use?
@HakaiKaien Ай бұрын
AI agents are a bit different from chat bots. With chat bots, you have a large language model responding to your prompt. With agents, you have a bunch of models talking among themselves to accomplish a task you give them. You can think about Agents as a company of employees. You give each of them roles and functions. You can use agents to build an application or a game for example.
@user-jc6tj2xt1p Ай бұрын
Wanna be yer cmdmp 😊
@sravan9253 4 күн бұрын
Understand the views that gen ai related stuff is getting, it would be better that you learn the stuff first properly and then make a video. Just reading the notebook is not achieving anything here, one can do the same with the colab link.
@matthewm8289 Ай бұрын
Its not Apache 2.0 licence, so you are very limited what you can do. Its not opensource!
@braadress Ай бұрын
Yes, it's opensource. Llama 3 is released under the CreativeML Open RAIL-M license. This license allows for broad use, including commercial use, while imposing certain restrictions aimed at ensuring responsible usage and maintaining safety.
@silvertechnolo3958 12 күн бұрын
it's not apache but it's certainly isn't limited. you own the products that are derived from its models and mostly you'll just have to display ",Made by Meta Llama 3" on your products about page. That said, the other issue is if your use base reaches a threshold then you have to renegotiate a new license and that could be when they actually try to cut into ip or profits etc.
@my-financial-wealthblog4423 Ай бұрын
I watched your video. Understood nothing.
@b6234 Ай бұрын
I stopped at "10x better" I will make my life 100 time better by not watching
@ramezdemitry3249 Ай бұрын
NameError Traceback (most recent call last) in () 11 {}""" 12 get_ipython().system('pip install tokenizer') ---> 13 EOS_TOKEN = tokenizer.eos_token # do not forget this part! 14 def formatting_prompts_func(examples): 15 instructions = examples["instruction"] NameError: name 'tokenizer' is not defined what shall i do here?
@dennisdemers9880 Ай бұрын
I joined the community but I don't know how to access it. Or when are the weekly meetings.? Trying to generate a python program as it turns out it's getting more and more sophisticated. Just llama three better at it than Chad gbt4
@DavidOndrej Ай бұрын
You can access it with the same link. The weekly meetings are on Tuesday and Saturday - more details in the "Calendar" tab at the top www.skool.com/new-society/calendar
@Sunshine-vd3bf Ай бұрын
It would be great if you could make a video on how to create datasets for fine tuning using LLM's/Agents!
Scott Ingram
Рет қаралды 5 М.
AI Jason
Рет қаралды 213 М.
How to scrape the web for LLM in 2024: Jina AI (Reader API), Mendable (firecrawl) and Scrapegraph-ai
LLMs for Devs
Рет қаралды 82 М.