ipex-llm/python/llm/example/GPU/LLM-Finetuning/HF-PEFT

Finetuning on Intel GPU using Hugging Face PEFT code

This example demonstrates how to easily run LLM finetuning application of PEFT use IPEX-LLM 4bit optimizations using Intel GPUs. By applying IPEX-LLM patch, you could run Hugging Face PEFT code on Intel GPUs using IPEX-LLM optimization without modification.

Note, this example is just used for illustrating related usage and don't guarantee convergence of training.

0. Requirements

To run this example with IPEX-LLM on Intel GPUs, we have some recommended requirements for your machine, please refer to here for more information.

1. Install

conda create -n llm python=3.9
conda activate llm
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
pip install transformers==4.34.0 datasets
pip install fire peft==0.5.0
pip install oneccl_bind_pt==2.1.100 --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ # necessary to run distributed finetuning
pip install accelerate==0.23.0
pip install bitsandbytes scipy

2. Configures OneAPI environment variables

source /opt/intel/oneapi/setvars.sh

3. Finetune

This example shows how to run Alpaca LoRA Training directly on Intel GPU.

cd alpaca-lora
python ./finetune.py --base_model "meta-llama/Llama-2-7b-hf" \
                     --data_path "yahma/alpaca-cleaned"