LLAMA-3 🦙: EASIET WAY To FINE-TUNE ON YOUR DATA 🙌
Vložit
- čas přidán 19. 05. 2024
- Learn how to fine-tune the latest llama3 on your own data with Unsloth.
🦾 Discord: / discord
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Patreon: / promptengineering
💼Consulting: calendly.com/engineerprompt/c...
📧 Business Contact: engineerprompt@gmail.com
Become Member: tinyurl.com/y5h28s6h
💻 Pre-configured localGPT VM: bit.ly/localGPT (use Code: PromptEngineering for 50% off).
Signup for Advanced RAG:
tally.so/r/3y9bb0
LINKS:
Announcement: llama.meta.com/llama3/
Meta Platform: meta.ai
unsloth.ai/
huggingface.co/unsloth
Notebook: tinyurl.com/4ez2rprt
Github Tutorial: github.com/PromtEngineer/Yout...
TIMESTAMPS:
[00:00] Fine-tuning Llama3
[00:30] Deep Dive into Fine-Tuning with Unsloth
[01:28] Training Parameters and Data Preparation
[05:36] Setting training parameters with Unsloth
[11:03] Saving and Utilizing Your Fine-Tuned Model
All Interesting Videos:
Everything LangChain: • LangChain
Everything LLM: • Large Language Models
Everything Midjourney: • MidJourney Tutorials
AI Image Generation: • AI Image Generation Tu... - Věda a technologie
Thank you!
More fine tuning case studies please on Llama 3!
Much appreciated 🙏 your presentation on this!
Will be making alot more on it. Stay tuned.
Thank you so much for sharing this was wonderful, I have a question, I am a beginner in LLM model world, which playlist on your channel can I start from ?
Thank you
thank you so much for this useful video!
Thank your very much for your great video. I ran the workbook but did not manage to find the GGUF files on Huggingsface. I put in my HF-Token, but that did not work. Do I have to change the code?
Was having such a hard time training llms before this, thankyou
glad it was helpful
Great video mate. How can i add more than one dataset ?
great video.
But how to add more than one datasets ?
This video lacks alot of helpful info... Anyone can just open the examples and read them just the same as you did. I would have liked to be given extra detail and tips about how to actually do fine-tuning... Some of the topics I am struggling with include, how to load custom data, how to use a different prompt template, how to define validation data, when to use validation data, what learning rates are good, how do i determine how many epochs to run... Im sorry buddy, but I have to give this video a thumbs down as it really truly and honestly dosent provide any useful info that isnt already in the notebook.
Mediatek's Dimensity chips + Meta's Llama 3 AI = The dream team for on-device intelligence.
Amazing, thanks!
Glad you like it!
Excellent thank you
Hello
ilpossible to generate gguf, compilation problem …
Did you try it ?
Can you make a video on how to use local llama 3 to understand large c++ or c# code base
search for ollama,
One more comment :-). this Video is about fintung a model, but there is no real explanation why. We finetune with the standard Alpaca dataset, but there is no explanation why. It would be great if you could do a follow up and show us how to create datasets.
How to actually train models? And I mean non-supervised training where I have a set of documents and want to learn on it and probably find author's 'style' or tendency?
You need to create some process to transfer all the knowledge in these documents in the form of "prompt":"best output". Usually we use an team of agents to do it for us.
Fantastic work and always love your videos! :)
Thank you
Thanks
Is there a way to sort of „brand“ llama 3. So that the model responds to „Who are you?“ a custom answer?
Thank you!
Yes, you can just add that as part of the system message
I have already finetune using unsloth for testing purpose.
Great, how are the results looking?
@@engineerprompt great results and thanks for your support to AI community
Bro can you tell me about unsloth, how it is different from the basics of using Qlora?
And also I used Qlora for Fine-tuning llama 2, can I just paste llama 3 model I'd to use in place of that?
I hope you understood my question, waiting for your reply 😊
@@TheIITianExplorer unsloth library is very useful library for finetune using LoRA technique . QLoRA is Quantization and LoRA so if use Unsloth then the same output you will get as unsloth already quantise the LLMs
What datasets did you fine tune it on? Have you run any benchmarks?
How do you train a model by adding the knowledge in a book, which will like only have 1 column of text?
In that case, you will have to convert the book into question answers and format it in the similar fashion. You can use an LLM to convert the book to QA using an LLM
Awesome, thanks
🙏
Regarding the save option. Do I have to delete the parts that I dont what, or how does this work?
You can just comment those parts. Put # in front of those lines which you don't need.
Have you ever thought about writing a no-code fine-tuning on premise app?
There is autotrain for that
great it was quick
Thank you! but Mac m3 max can use mlx to fine-tune?
Yes
Hi, nice video. But how to finetune model on my codebase?
You can use the same setup. Just replace the instruction and input with your code.
@@engineerprompt how to divide code on "question - answer" pairs? or I can place whole codebase to single instruction
One thing I am unsure of is how to transform my data into a training set. I have the target format: the written body of work, but no "instruction" or "input" of course. I've seen some people try to generate it with ChatGPT, but this seems counter-intuitive. There must be an established method of actually manipulating data into a training set. Where is that piece?
You will need to have a {input, response} pair in order to fine-tune an instruct model. Unfortunately, there is no way around it unless you are just pre-training the base model.
Next week Gemini 2 with text to video 😂
We fine
Hi, please what if we have already downloaded a gguf file? How do we apply that locally?
I am not sure if you can do that. Will need to do further research on it.
Sir, we cannot open the colab website...
Already solved...
great
Hello can I fine tune it using colab free version?
This is using the free version
So 60 steps is to low. But what it a good number of steps?
Usually you want to set epochs to 1 or 2
@@engineerprompt So 60 to120 steps max, since one epoch is 60 steps?
can i fintune using colab free gpu?
Yes, this uses the free collab.
@@engineerprompt love you broooo
They messed up releasing llama 3 because it believes it is sentient
Why you didnt provide any examples of training. It would make this video 10 times better.
that is coming...
It's a Zuckerberg free AI........that makes me wonder. And you have to agree to hand over contact info and what else, I wonder ?
Don't share trash
you really should just make videos in your own language because who the fk can even understand what you are saying?