Fine-Tune Large LLMs with QLoRA (Free Colab Tutorial)

Показать описание

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

❤️ If you want to support the channel ❤️
Support here:

Рекомендации по теме

Комментарии

Little correction: the target_modules in the LoraConfig should include the dense layers as well, as per paper.

alealejandroooooo

Would love to see more videos on preparing training data for domains.

Classification, summarization, sentiment analysis all seem clear enough. But more complex tasks are a bit if a mystery.

For example, training question answering and other instruction for a specific knowledge base like a code library, book, etc. How can the original content from the source be used in the response? Is fine tuning a use case, or can we only use embeddings for domain specific knowledge?

robxmccarthy

please finetune using any custom dataset like question answering and make a video that will be helpful thanks

saivivek

I have been following your channel for a while now. All your videos are informative, there's no clickbait material. I am a YouTube myself (food vlogger, not tech vlogger LoL) and I know the condition of Indian YouTube nowadays. Comparing to that your videos are gems in themselves. About this video, can you tell us approximately how much time does it take to complete the fine tuning process (approximately)? Will it reduce if I subscribe to Colab Pro? Are there any other free or relatively cheaper alternatives than Colab?

HashtagTiluda

Is it possible to use QLoRA to fine-tune LLMs on labelled data? My downstream task is supervised text classification

marcelgeller

Hey what is the best Server site to Host your LLM?i mean for massiv use Not localy

ohnoman

I have a question: the dateset has features: ['quote', 'author', 'tags', 'input_ids', 'attention_mask'], how does the trainer know which feature to select for training (fine-tune)?

weizhili

The Last Ben repository is not working on free Collab anymore, can you create a video on alternatives?

DKUnhinged

What is the max parameter size which a 16 GB GPU can train up to with QLORA?

incameet

@1littlecoder: It's giving you results and it is supposed to give you this exactly because it's a sentence completion model. so if you input: "Elon Musk" -> It is trying to complete the sentence. thank you :)

Deshwal.mahesh

How do you correct "CUDA out of memory" error in free version of Google Colab? I get that when finetuning an LLM

ifeanyiidiaye

0.08 %, not 8 %. This is directly given in percentage, it does not sum up to 1, but 100. But a great video!

skyr-inf

Do you have any techinique to understand which target modules should I select for a custom model?
As you said, in this case it was target_modules=["query_key_value"], but if it was another ....

aiplaygroundchannel

Why would I bother fine tuning a giant 65B model that I wouldnt be able to run anyways? So that I can quantize it or something? And that makes me wonder, should you fine tune then quantize, or quantize then fine tune?

nattyzaddy

I think it's actually .08%. Not 8% as you said

ixwix

I know what Lora is. I learnt what Qlora is now.

vichitra-yt

can you tell how to train using like a csv file or something from google drive?

LEGENDSNEVERDIE

hi how can we the original implementation behind any library .i know its a basic question how do we check .like qlora or lora etc?ccan u suggest please

aishwaryap.s.v.s

Hello sir. I am completely newbke plz make videos on how we can run AIs locally for from (noob guide). Also tell computing source requirements for Corresponding AI. Thanks.

faisalali

Could you explain how I can retrain the new model? Also How to use in further scripts the new trained model?

nikandr

Fine-Tune Large LLMs with QLoRA (Free Colab Tutorial)

Fine-Tune Large LLMs with QLoRA (Free Colab Tutorial)

QLoRA—How to Fine-tune an LLM on a Single GPU (w/ Python Code)

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

LoRA - Low-rank Adaption of AI Large Language Models: LoRA and QLoRA Explained Simply

LoRA & QLoRA Fine-tuning Explained In-Depth

Fine-tuning Large Language Models (LLMs) | w/ Example Code

Fine-tuning LLMs with PEFT and LoRA

Fine-tuning Llama 2 on Your Own Dataset | Train an LLM for Your Use Case with QLoRA on a Single GPU

Part 1-Road To Learn Finetuning LLM With Custom Data-Quantization,LoRA,QLoRA Indepth Intuition

Fine Tuning LLM Models – Generative AI Course

Quantization in Fine Tuning LLM With QLoRA

QLoRA is all you need (Fast and lightweight model fine-tuning)

Insights from Finetuning LLMs with Low-Rank Adaptation

What is LoRA? Low-Rank Adaptation for finetuning LLMs EXPLAINED

🐐Llama 2 Fine-Tune with QLoRA [Free Colab 👇🏽]

'okay, but I want Llama 3 for my specific use case' - Here's how

LoRA explained (and a bit about precision and quantization)

Fine-tuning LLM with QLoRA on Single GPU: Training Falcon-7b on ChatBot Support FAQ Dataset

Finetune LLAMA2 on custom dataset efficiently with QLoRA | Detailed Explanation| LLM| Karndeep Singh

QLoRA - Efficient Finetuning of Quantized LLMs

QLoRA paper explained (Efficient Finetuning of Quantized LLMs)

Understanding 4bit Quantization: QLoRA explained (w/ Colab)

FREE LLM fine-tuning with QLORA

Low-rank Adaption of Large Language Models: Explaining the Key Concepts Behind LoRA