We will finetune an open-source LLM using PEFT, LoRA to perform sepecialized task using Prompt Engineering.
conda create -n llm_finetuning python=3.11
conda install anaconda::jupyter
conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia
pip install transformers
pip install datasets
pip install peft accelerate
pip install trl
pip install scipy
pip install bitsandbytes