Steps By Step Tutorial To Fine Tune LLAMA 2 With Custom Dataset Using LoRA And QLoRA Techniques

In thsi video we will be dicussing about how we can fien tune LLAMA 2 model with custom dataset using parameter efficient Transfer Learning using LoRA :Low-Rank Adaptation of Large Language Models.
Code: drive.google.com/file/d/1Bd7c...
-------------------------------------------------------------------------------------------------
Support me by joining membership so that I can upload these kind of videos
/ @krishnaik06
-----------------------------------------------------------------------------------
►AWS Bedrock Playlist: • Generative AI In AWS-A...
►Llamindex Playlist: • Announcing LlamaIndex ...
►Google Gemini Playlist: • Google Is On Another L...
►Langchain Playlist: • Amazing Langchain Seri...
►Data Science Projects:
• Now you Can Crack Any ...
►Learn In One Tutorials
Statistics in 6 hours: • Complete Statistics Fo...
End To End RAG LLM APP Using LlamaIndex And OpenAI- Indexing And Querying Multiple Pdf's
Machine Learning In 6 Hours: • Complete Machine Learn...
Deep Learning 5 hours : • Deep Learning Indepth ...
►Learn In a Week Playlist
Statistics: • Live Day 1- Introducti...
Machine Learning : • Announcing 7 Days Live...
Deep Learning: • 5 Days Live Deep Learn...
NLP : • Announcing NLP Live co...
---------------------------------------------------------------------------------------------------
My Recording Gear
Laptop: amzn.to/4886inY
Office Desk : amzn.to/48nAWcO
Camera: amzn.to/3vcEIHS
Writing Pad:amzn.to/3OuXq41
Monitor: amzn.to/3vcEIHS
Audio Accessories: amzn.to/48nbgxD
Audio Mic: amzn.to/48nbgxD

[@kalyandey5195]

Amazing !!! I have red the book -"Generative AI on AWS" today and learnt all the concepts of quantization, PEFT, LoRA, QLoRA and you have uploaded the video for the same!! Thanks a lot!!

[@shivashankarmrampur8800]

Can you please share the link of book if you have

[@VivekPatel-sj3up]

Book name??

[@mysticlunala8020]

@@VivekPatel-sj3up He literally told the book name. Are you guys blind?

[@omarhalabi889]

have some manners @@mysticlunala8020

[@headhunterlovish5111]

Can U please send me the book or link for it

[@zulaysolis5145]

Wow thanks for breaking it down step by step.

[@shakilkhan4306]

I started my fine tuning journeys , hope it would be something interesting

[@AbdullahiAhmad-Babura]

Amazing following for a long time you are doing well

[@DataDorz]

Amazing video Krish, Can you also make a video on how to build RAG based LLM for Q&A over multiple documents where we can actually compare between two or more documents.

[@bluelightning5350]

Please make vidoes on theoretical concepts such as LLM model internals, Mixture of Experts, RLHF and so on.

[@rishiraj2548]

👍

[@VivekPatel-sj3up]

+1

[@saqibmumtaz9380]

+1

[@pedroluisbroca204]

This guy's excitement for NLP is adorable but man needs to get out more, the real world is calling!

[@arri5812]

thank you sir for this video, please make videos on theortical concepts needed to understand this fine tuning process. It will mean alot thanks sir

[@rishijain8231]

Amazing video! Can you please make a video on the theoretical aspects as well?

[@avanthikar2608]

Can you please upload videos indepth of how different prompting techniques like chain of thought, self consistency, knowledge generation etc were practically used with which the outputs of the models based on use cases are getting improved

[@sajidchoudhary1165]

Yes, please make a theoretical video as well on all open source llms

[@AngelBautistaMartinez]

Mistral's medium posts helped me a ton, then found enterprise for hands on work

[@otakudnp3880]

does mistral have a medium page? but finding it

[@saqibmumtaz9380]

Please also make a video on mathematical concepts and the intuition behind the LLMs. Already subscribed and liked the video, as you are doing an amazing job.

[@vsneelesh3692]

need a theory content also sir . I would help in making the foundations stronger

[@oxydol3456]

it's working as charm wow.

[@user-zm7gq2lz1s]

Thank you for this amazing video. Can u also explain how to create custom dataset in Q/A format from the raw text and fine tune it and should we fine tune or use RAG if we want reponse from a particular domain only.Thanks

[@ramankhanna9526]

thanks for the video , it would be better if u can show documentation side by side with ur testing plz

[@Abdullah_kwl]

Make theocratical videos on PEFT, LoRA, QLoRA, how quantization work, how quantize a model and Mixture of experts works

[@sanjaykrish8719]

You are a gem ❤❤

[@markandsweep]

Thanks Krish

[@nasiksami2351]

Thank you for the video. The main issue I face from these tutorials is the custom dataset preparation part. Here also the dataset is loaded from HF. I have a tabular NLP classification dataset in my local. Let's say sentiment analysis dataset. How should I prepare the dataset and run the llm finetuning locally? Thank you again for this tutorial. I hope you'll show us the implementation of actual local, own dataset finetuning. Also, there's a paper called TabLLM, which uses LLM on numeric tabular datasets. Making a video on that one would be so much helpful regarding implementing it on the custom private dataset. Thank you again, and keep bringing good content as always

[@anushareddygudipati5169]

Amazing! Can you please make video on how to use fine tuned model in RAG.

[@KumR]

waiting for the ollama video buddy

[@bikramsubedi3456]

for tuning this model the format of dataset must be same or i may use any others format too such as row with text only without and [INST] or if labelled data are required then i use csv with two rows for prompt and answer??

[@sanadasaradha8638]

Actually this the video i want to ask you but you read my mind before I ask that why I am saying now Krish sir is mind reader

[@PranavBaviskar]

Thanks for the video. Could you please create an end-to-end implementation video where you use Streamlit and local CPU?

[@akandesoji3580]

Amazing how did you know all this sir😢😢😢😢

[@ssen081]

Please conduct sessions on running AI models on cloud platforms like AWS, Azue and Google

[@VijayKumar-ib3qc]

Hi Krish, Thanks for the video. What is the purpose of developing the model using PEFT? Is the objective is to mimic CHATGPT where you ask questions and you get the answer?

[@sanadasaradha8638]

Sir do a video on how to transfer the customer data into q&a format for fine tuning to llms

[@A.M.8181]

Can you tell me what dataset templates should be used for fine-tuning? What fields should be there? If I need the model to answer questions in chat mode, like a first-line support bot, make a summary of the text I insert - are these different sets and as a result different models? That is, it turns out that I need already 2 models, each solves a specific task? If, for example, there is a production department and a financial department in the company, then is it better to use 2 separate small models and they are tailored to a separate knowledge sphere or use one large one? Show how to fine-tune on a local computer in the VSC environment on an RTX4090 video card

[@dibyanshuchatterjee4126]

Can you please make a video on DPO fine tuning method and its implementation.

[@vinayyadav6522]

Hi Krish, Please make a complete video of bedrock llama2 chat further steps for providing the output as API to the front-end or to check on postman by passing inputs and inference parameters using fastapi or Django.

[@wasimmemon2284]

Hi Krish, I had a doubt: Will quantization decrease the accuracy of the whole model? Will that mean that we will get less accurate results?

[@flyingsnow1357]

Can we do fine tuning on unsupervised data?

[@ruiteixeira2324]

May I ask a question? I used your code to fine-tune llama2 7b-chat on my data and the code works perfectly, but for some reason my new LLM can't predict the EOS token. So, every time I ask the model to generate text, it will generate tokens until it reaches the max_length. I think there is something wrong with the way Lora is using this EOS token. Do you have any idea how to fix this? By the way, amazing video. Thanks.

[@user-rv9rn3ux9v]

Good tutorial!

[@divyagarh]

Thanks for uploading! how to create the dataset from your HTML/PDF content to train the model?

[@aravindraamasamy9453]

I want to integrate my database to the llm model , is it possible to finetune that. Can you show demo for integrating databses and fine tuning the llm model based on it.

[@abduljalilhassan1798]

Krish Naik please discuss how to evaluate the model ?

[@prashantagarwal4570]

@Krish- After done fine tuning of the model, how can I run the fine-tuned model on local machine

[@ArunkumarMTamil]

how is Lora fine-tuning track changes from creating two decomposition matrix? How the ΔW is determined?

[@vishalaiml1649]

Hi Krishnaik, can you please create a Series on securing LLM responses, and Guardrails as it is burning topic now a days. Sincere Request.

[@coldedkiller1125]

Sir this is a great video, but Please give a method that dont use hugging face to download the model, because we may have to train the same model again with new data. Also in the video we have download the model but how to load the model if it is locally available ?

[@ashish_sinhrajput5173]

what modification i need to do i i wanted to fine-tune this llama model on text-Summarization task... ?

[@tirthbhatt3340]

Hello krish could you please make videos on Auto gen?

[@fl028]

Hi everyone, I have a question about data preparation and fine tuning of LLMs. What should the data format look like in the fine tuning process? On the one hand, it can be pure text to add special knowledge to the LLM. On the other hand, the data set can be structured in question and answer / prompt and answer format. What do you think? Do you have any recommendations for me? Thank you and best regards!

[@tirthbharatiya2611]

hey Krish, why I'm not able to see course request form on TechNeuron and why there is no new content?

[@CosmosTraveler8008]

Sir can you create videos for evaluation of LLMs

[@TheAmazonExplorer731]

Please make a vido with demo that robot perform task using LLM

[@rahulhiware4049]

@Krish Can you load the fine-tuned model and then test/check it on the test data? In last code snippet I guess you are using the base model to get the results. Please correct me if I am wrong. Coping that line of code here which I am doubtful of. pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)

[@user-bl4wn6cr2i]

I have the same doubts. It seems it is picking the old base model and not the fined-tune one. Correct me if I am wrong

[@pranabsingharoy3270]

Why you are train for 1 epoch only? What will be the optimal number of epochs?

[@user-vo5ce6kn5t]

I have already run this script one month ago, but this model cannot provide accurate answers as on custom data on which this llama2 model is trained .

[@user-xo3cu7nq1z]

from where did you learn ? can you share some resources , so that i can learn all of these from one place ?

[@shaikirfanrahim7334]

Please make video on oneDNN

[@SyafieWork]

If I am using langchain, can i still use this method?

[@gokulraj6633]

Will the same code work for llama 13b chat . If not can you share Collab for fine tuning llama 13b .

[@AppleFlickFix]

Hi folks, can anyone help? he had taken from the hugging-face for the final demonstration of the output but we need to test the fine-tuned model right?

[@ravikumar46931]

Can we train this model locally by creating a virtual environment (e.g. conda) ?

[@ashishmehra5143]

It is possible but you need a very high VRAM to process.

[@gideongyimah217]

Can you please upload a video on how to finetune LLM model to work on or understand local language given a dataset on local languages

[@ashishmehra5143]

Finetuning happens when you cannot train the model for each user or each use case. If you want the model to work in a specific native language, the Llama2 model should have been trained in the same native language. Remember you are training the model with the data and the current Llama2 model is training on the English dataset.

[@yajuvendra15]

Hello Krish, May I know how can we deploy this as an app in a kubernetis enviroment. thanks

[@nimesh.akalanka]

How can I fine-tune the LLAMA 3 8B model for free on my local hardware, specifically a ThinkStation P620 Tower Workstation with an AMD Ryzen Threadripper PRO 5945WX processor, 128 GB DDR4 RAM, and two NVIDIA RTX A4000 16GB GPUs in SLI? I am new to this and have prepared a dataset for training. Is this feasible?

[@somtirthadas9347]

RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver. I'm facing this error in google colab while running the GPU compatibility part. What can be the solution?

[@Hizar_127]

I have a 50k sample dataset i want to fine tune the model.. can i do with this code ??

[@sanjanakumar7525]

Can you please update the link to the code? The one given in the description does not work anymore

[@raghuvallikkat3384]

Hi Krish, Hi , I want to fine tune a code generator model with our organisational data specific to embedded Software. code generated should be specific to the chipset we are using. I was thinking of using starcoder/CodeLLAMA as a base model and fine tune with QLORA. But I dont have much clarity of the format in which I should prepare the custom data set. Can you please help on this. Will joining the group with subscription will help to get some 1:1 guidance

[@TechKnowledgeForYou780]

Hi Sir, Thanks for the information. Could you please share that pdf(Parameter - Efficient Transform learning for NLP).

[@user-lp3me7kf1w]

downloaded the dataset and entered my own one prompt template by replacing other, and was not able to achieve the result for it, Kindly help me.

[@azkarathore4355]

Can we finetune llama3 model for machine translation task

[@mayankmaurya9990]

Hi krish, If I have client data and don't want to load from huggingface then How can I do this?

[@dipali5562]

buy 4bit quantization don't u think we will be loosing information ?

[@Mintusir9]

Hello sir ❤ Can you make a welding detection project using AI Is it possible to you or not If you make then please make

[@ashishmehra5143]

You do not need an LLM model for it. Wedding possibility is a classification problem and it is very easy to make a model if you know logistic regression or decision tree algorithm. These are week learners with a low accuracy but your use case is solvable by the said algorithms.

[@Mintusir9]

@@ashishmehra5143 you can do this project then please make a video

[@user-wj4ce4gi6n]

Can we use this for other languages such as Arabic Thanks a lot!!

[@krishnaik06]

Yes u can

[@sanket9871]

How can I save the fine tuned model locally?

[@jadedboy-kx3vm]

How can i get my model in gguf format?

[@user-xn3ir2yc6m]

hi everyone, can anyone help very quickly print(res[0]['generated_text']). it gives us both input and output. is there anyway i can get only output result?

[@sumayyaafreen3499]

Can we use LLAMA for urdu language applications?

[@sayantikachatterjee5032]

why we set fp16=False, bf16=False in training_arguments = TrainingArguments() ?

[@nareshmalviya3100]

When i load the model. I facing error config.json not appear. And my model saved adapter_config.json Please provide solution.......

[@vijaydas2962]

looks like a typo!! Are we not supposed to be using "new_model" instead of "model" while testing the fine tuned model? I'm referring to this line-----> pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200). I think correct argument should be --> model=new_model instead of model=model ??

[@vidhanrathore2296]

Hi Your video is amaizing but I am not able to assess the code can provide me the github link I can utilize it. Please please............

[@lixiasong3459]

Sir, can I run the code on my local vs code?

[@ashishmehra5143]

Yes if your local compute has enough processing power to run it.

[@FuzzyLab]

How i can pass my model to .gruff ?

[@rohanpandey9957]

need a whole playlist on llms sir

[@pratibhagoudar6817]

Hi krish sir! I have worked on this script 2 days back, and I am eagerly waiting for your explanation about this llama. And my doubt is that, I think you didn't gone through this cell, "Reload the fp16 and merge it with lora weights " Explain this code cell and how it will merge and where it could be stored. For this particular block error : I'm getting out of the memory issue . And waiting for math's behind peft and theriotical knowledge... I hope this comment you will read,, And hope for response to my question!!! Thank you🌹

[@user-vo5ce6kn5t]

you should change your google Colab memory runtime

[@pratibhagoudar6817]

@@user-vo5ce6kn5ti have worked with it's T4 gpu.. Do i need to change to another runtime?

[@abduljalilhassan1798]

We are still waiting for theoretical part

[@enough200]

why dont you explain the theory also

[@krishnaik06]

Next video

[@k4f]

This video makes my LoRA hard

[@explorewithshiljoy]

Apologies, but upon viewing your video, I found the explanation lacking. It's crucial to have a strong initial explanation, especially when presenting more intricate concepts like fine tuning.

[@sparkledark3713]

He said it's an overview. Just a rundown before starting the video:

[@user-mi3zv2jd6i]

CaSUal nhi sir ji....CaUSal...!!!

[@agrawal1207]

The video was just to show off your knowledge, it wasn't a tutorial to anything

[@snehitvaddi]

Hey! Facing this issue with Langcahin loader: AttributeError: module 'numpy.linalg._umath_linalg' has no attribute '_ilp64' Literally dying to resolve this. Please help