filmov
tv
PEFT LoRA Explained in Detail - Fine-Tune your LLM on your local GPU
Показать описание
Your GPU has not enough memory to fine-tune your LLM or AI system? Use HuggingFace PEFT: There is a mathematical solution to approximate your complex weight tensors in each layer of your self-attention transformer architecture with an eigenvector and eigenvalue decomposition, that allows for a minimum memory requirement on your GPU / TPU.
The HuggingFace PEFT library stands for parameter-efficient fine-tuning of transformer models (LLM for language, Stable Diffusion for images, Vision Transformer for vision) for reduced memory size. And one method of PEFT is LoRA: Low-rank Adaptation of LLMs.
Combined with setting the pre-trained weights to non-trainable and maybe even consider a 8bit quantization of your pre-trained LLM model parameters, a reduced memory footprint of adapter-tuned transformer based LLM models achieves SOTA benchmarks, compared to classical fine-tuning of Large Language Models (like GPT, BLOOM, LLama or T5).
In this video I explain the method in detail: AdapterHub and HuggingFace's new PEFT library focus on parameter-efficient fine-tuning of transformer models (LLM for language, Stable Diffusion for images, Vision Transformer for vision) for reduced memory size.
One method, Low-rank Adaptation, I explain in detail for an optimized LoraConfig file when adapter-tuning INT8 quantization models, from LLMs to Whisper.
Follow up video: 4-bit quantization QLoRA explained and with colab Notebook:
#ai
#PEFT
#finetuning
#finetune
#naturallanguageprocessing
#datascience
#science
#technology
#machinelearning
The HuggingFace PEFT library stands for parameter-efficient fine-tuning of transformer models (LLM for language, Stable Diffusion for images, Vision Transformer for vision) for reduced memory size. And one method of PEFT is LoRA: Low-rank Adaptation of LLMs.
Combined with setting the pre-trained weights to non-trainable and maybe even consider a 8bit quantization of your pre-trained LLM model parameters, a reduced memory footprint of adapter-tuned transformer based LLM models achieves SOTA benchmarks, compared to classical fine-tuning of Large Language Models (like GPT, BLOOM, LLama or T5).
In this video I explain the method in detail: AdapterHub and HuggingFace's new PEFT library focus on parameter-efficient fine-tuning of transformer models (LLM for language, Stable Diffusion for images, Vision Transformer for vision) for reduced memory size.
One method, Low-rank Adaptation, I explain in detail for an optimized LoraConfig file when adapter-tuning INT8 quantization models, from LLMs to Whisper.
Follow up video: 4-bit quantization QLoRA explained and with colab Notebook:
#ai
#PEFT
#finetuning
#finetune
#naturallanguageprocessing
#datascience
#science
#technology
#machinelearning
0:40:55
PEFT LoRA Explained in Detail - Fine-Tune your LLM on your local GPU
0:15:35
Fine-tuning LLMs with PEFT and LoRA
0:17:07
LoRA explained (and a bit about precision and quantization)
0:04:38
LoRA - Low-rank Adaption of AI Large Language Models: LoRA and QLoRA Explained Simply
0:14:39
LoRA & QLoRA Fine-tuning Explained In-Depth
0:46:56
PEFT w/ Multi LoRA explained (LLM fine-tuning)
0:08:22
What is LoRA? Low-Rank Adaptation for finetuning LLMs EXPLAINED
0:26:55
LoRA: Low-Rank Adaptation of Large Language Models - Explained visually + PyTorch code from scratch
0:19:17
Low-rank Adaption of Large Language Models: Explaining the Key Concepts Behind LoRA
0:22:35
LoRA & QLoRA Explained In-Depth | Finetuning LLM Using PEFT Techniques
0:32:55
Part 1-Road To Learn Finetuning LLM With Custom Data-Quantization,LoRA,QLoRA Indepth Intuition
0:13:27
LLM2 Module 2 - Efficient Fine-Tuning | 2.3 PEFT and Soft Prompt
0:28:18
Fine-tuning Large Language Models (LLMs) | w/ Example Code
0:22:44
Part 2-LoRA,QLoRA Indepth Mathematical Intuition- Finetuning LLM Models
0:20:19
Finetune LLM using lora | Step By Step Guide | peft | transformers | tinyllama
0:08:37
Efficient Large Language Model training with LoRA and Hugging Face PEFT
0:14:45
Fine-Tune Large LLMs with QLoRA (Free Colab Tutorial)
0:24:11
Fine-tuning LLMs with PEFT and LoRA - Gemma model & HuggingFace dataset
0:26:45
Steps By Step Tutorial To Fine Tune LLAMA 2 With Custom Dataset Using LoRA And QLoRA Techniques
0:14:36
Fine-tune LLama2 w/ PEFT, LoRA, 4bit, TRL, SFT code #llama2
0:27:19
LoRA: Low-Rank Adaptation of LLMs Explained
0:42:06
Understanding 4bit Quantization: QLoRA explained (w/ Colab)
0:30:13
LoRA Explained
0:05:45
PEFT Fine Tuning - Parameter Efficient Fine Tuning Methods
Комментарии