How to hack a LLM using PyReft (using your own data for Fine Tuning!)
Vložit
- čas přidán 4. 05. 2024
- 🚀 Sign up to the newsletter
go.coursesfromnick.com/newsletter
👨💻 Sign up for the Full Stack course and use CZcams50 to get 50% off:
www.coursesfromnick.com/bundl...
Hopefully you enjoyed this video.
💼 Find AWESOME ML Jobs: www.jobsfromnick.com
🤖 Get the Code: github.com/nicknochnack/PyReft
Disclaimer: This has been developed for academic purposes. Nothing herein is financial advice, and NOT a recommendation to trade real money. Please use common sense and always first consult a professional before trading or investing.
Oh, and don't forget to connect with me!
LinkedIn: bit.ly/324Epgo
Facebook: bit.ly/3mB1sZD
GitHub: bit.ly/3mDJllD
Patreon: bit.ly/2OCn3UW
Join the Discussion on Discord: bit.ly/3dQiZsV
Happy coding!
Nick - Věda a technologie
Hey, I'm one of the authors of the ReFT paper and pyreft, thanks for making this awesome walkthrough! Let us know if you had any trouble setting anything up / you want any improvements to the documentation :)
First up, I just want to say you are freaking amazing! Congratulations to you and your for tackling the research and creating such a straight forward library! Would love some clarity on the unit location mapping during inference!
Before I watch the video, just want to let you know that I was really waiting for you to do an LLM Finetuning video. Really excited for this one
Slow tokenizers (use_fast=False) are those written in Python inside the Transformers library, while the fast versions (use_fast=True) are the ones provided by Tokenizers, which are written in Rust.
Ohhh got it! Cheers man, gotta do a deep dive on transformers soon.
Welcome Back ! The Nicholas's community need you to provide edge production topics like this :DDDDDD
I love your Videos. I always learn new things. Thank you so much. You are such an awesome guy, please keep doing it, I always wait for new content from you.
Excellent video that I need to try. Thank you for sharing.
Cheers Ken!! Lmk how you go!
always on top with the value
Thanks a mil man!!
Does this work with Mac M3 pro? Any parameters I’d need to change? Looks great!! Very excited about this
Hey Nick I am getting this error while trying to train the pyreft model
TypeError: Object of type type is not JSON serializable
Great video Nick! Do you know what params should I use when working on Macbook M3 Max. In the video you set_device('cuda').
Hi man i have one doubt you should clear that (book vs online tutorials/course) which is best
What you learn for programming.
Hey, i think i saw once on your ideas list something about a self driving car, possible to do that? Would be really interested :)
Hi sir 👋.
It is possible to used the same code for binary classification like the labels are 0 and 1 only ?
Instead of prompt and response i have a dataset contains the headlines and labels.
Hi, I have a question. Can we write a reinforcement learning model that connects to a real environment instead of simulated environments?
Great video mate! How easy would this be to apply to the Llama 3 version of instruct 8b?
Gotta double check if pyvene supports it but I can't imagine it'd be that hard. Might tackle that next week!
Love your videos ❤😅
Hey Nicholas could you do a video about video classification ??? It’s been so hard to learn about it…
Good one 🎉
Cheers!!
for this specifc Q/A purpose isn't RAG particularly useful than fine-tuning ?
I'm struggling to figure out the format for phi3 mini dataset. Any ideas? Can I still do it exactly like the video for my case?
Also great video perfect timing for just what I needed
Can take a look, needs to be in HF format for it work - there's a list of models on the pyreft/pyvene site that lists compatible models.
How long have you been an ai engineer? I want to start i don't know where and what math and level of math needed. It would be very useful if you gives clear road map
Please do make a video on fine tuning LLM with your own dataset using transformers trainer. Thank you.
This week, working on qlora atm.
Is that safe to train LLM on corporate machine ?
Hello Nicholas can you help on how to build a resume filtering using machine learning and NLP to quickly and accurately filter and rank resumes based on job description.Can you please if there is any step by step video I can watch for it,kindly recommend
anyone knows how to push the finetuned model to hf hub?
Hi bro can you redo beginner to advance ml projects for 2024 , big fan was with you since 2k subscribers ,😊😊😊😊❤❤❤❤❤
I second this Notion lol
Oh, like the old series? Just staight up Deep Learning projects from scratch?
@@NicholasRenotte nope , the beginner to advance ml projects , thanks for replying, big fan 🥰🥰🥰🥰🥰
Hi Nick. Great video. Im trying to run the face mask detection model from your previous videos. I think the Object detection api is outdated i have reached out to you on fb. can you please help me out for a few minutes?
Hey, can you make Voice based payments application for regional languages??
THANK U
Anytime, glad you liked it!
Hey I am an old sub watching your great content for about a year I have a challenge for you how about you build an LLM from scratch and then use human reinforcement learning plz
Yay UTS!
Ayyyy, wait you're a UTSer as well?!
Hi, Nick we are waiting for the Transformers lectures.
Yeah was trying to punch it out this week, realised I had a ton more to do on it. This week is probs qlora.
👏🏽
Ayyy, thanks babe!
Please make long videos this 15 min thing is kinda too constrained
But it was 40 minutes? 😅
First
Ayyyyy
First 😂
Am i not the first?
👀😅
Hi Nic, I support your video, I try your old video from 2 years ago about Real Time Sign Language Detection with Tensorflow Object Detection and Python Deep Learning SSD and I have problem with step 2 Create TF records in 23:15 cause i got red output (error)
here the error
Traceback (most recent call last):
File "C:\Users\ACER\Tensorflow\scripts\generate_tfrecord.py", line 27, in
import tensorflow.compat.v1 as tf
File "C:\Users\ACER\AppData\Roaming\Python\Python311\site-packages\tensorflow\__init__.py", line 45, in
from tensorflow.python import tf2 as _tf2
File "C:\Users\ACER\AppData\Roaming\Python\Python311\site-packages\tensorflow\python\tf2.py", line 21, in
from tensorflow.python.platform import _pywrap_tf2
ImportError: DLL load failed while importing
hope you see my comment and help me, thanks before ✨