Home > AI Solutions > Artificial Intelligence > White Papers > Model Customization for Code Creation with Red Hat OpenShift AI on Dell AI Optimized Infrastructure > Software design
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters designed for general code synthesis and understanding. This solution focuses on Code Llama and fine-tuning using LoRA technique with a dataset available from Hugging Face as an example for developers. The developers can use these guidelines to customize these models according to their datasets based on their own software repositories.