"okay, but I want Llama 3 for my specific use case" - Here's how
ฝัง
- เผยแพร่เมื่อ 16 พ.ค. 2024
- If 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...
If you want a personalized AI strategy to future-proof yourself and your business, join my community: www.skool.com/new-society
I highly recommend it, the community is fabulous!
It would be great if you could make a video on how to create datasets for fine tuning using LLM's/Agents!
It can be so helpful!
Thank you for this video. The topic of fine-tuning was very interesting to me.
Keep up the amazing work bro.
You provide us valuable knowledge.
yes dataset made by agents ! Thx for all your content !
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.
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.
love the videos thanks a lot for taking the time to put them out
LOVE these empowering videos, thanks for sharing 🙏
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.
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!
hello, do you know if it's possible to fine tune with ebook pdf on a specific domain (financial, medical...) ?
Yes, please make a video on how to create the datasets for fine tuning AI - and Thanks for all you do.
Yes please. Team of Agents to create a fine tuning data set from your proprietary data.
TY I finally trained my first model. Here's another vote for the how to create the fine tuning using LLM agents.
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.
Nice to see you here!
Excellent information ❤
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?
As I am , i need to know this
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
You're putting out some great content
Great work... Thanks for the tutorial ❤❤❤
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?
Very useful information!
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.
It would be an interesting topic for a video on how to use agents to generate data for fine-tuning.
please make a video on how to create datasets!
Thank you...
Where is fine tuning models stored and how can I find and download it for use?
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!
Please do make a video on creating datasets, both with and without the use of agents!
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
I would love to see a dataset fine tuning tutorial!
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?
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
what's the dataset like if train for conversations? for example: in a conversation, we have one instruction, multi inputs, and multi outputs
any way to input images as well to fine tune on image and text at the same time?
If there a way to generate the dataset input output data from contextual data like emails and q&a from website forums?
awesome David
love the 3 primary colors at 10:12 :)
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!
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............
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.
Thanks alot !!! it is really helpful :)
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. 👍
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 :)
Hey what about phi-3..?
did you try finetuning gpt3.5 on the playground?
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
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.
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.
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.
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.
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 ?
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
Hey David, thanx for this awesome served topic! Exactly what I need to get through this week 😅
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.
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
I had same idea
@@ASchnacky y'a that would be great if we can do that without coding ,good luck
Nice, how to deploy the saved model?
I want to Create a Lama 3 legal Assistent. I would be happy in you can Show a data prep example
How about Fine-Tuning vs. RAG in those specific things?
open AI has its own API for fine-tuning
Yeah, it would be nice if you could set up a video showing how to automatically generate datasets for fine-tuning LLMs… Tks
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.
your right headphone will be over your eye soon ;D Thanks for the great content David!
If pushing to hugging face, no config.json so won’t work
More content with lama!!! 🙏❤️
Yeah, a video on agents for finetuning datasets with a fine tuned LLMs, and used by agents for a real world application.
I'm a subscriber, please make the making dataset video
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.
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.
@@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
Can I do this in any language?
Do you ever sleep? Wow this is amazing 🎉👏
NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs:
Please bro make a video for create datasets
What's an example of what you or someone else has created with this?
Lava FRI?
colab doesnt work....
Fine tune or RAG
its no longer april T.T
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?
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.
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.
I wish… not everyone joined at 77
Wanna be yer cmdmp 😊
Its not Apache 2.0 licence, so you are very limited what you can do. Its not opensource!
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.
I stopped at "10x better" I will make my life 100 time better by not watching
I watched your video. Understood nothing.
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
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
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?
It would be great if you could make a video on how to create datasets for fine tuning using LLM's/Agents!