StableCode Tutorial: A Step-by-Step Guide to Get Started

What is StableCode from Stability AI?

StableCode, the latest offering from Stability AI, is an innovative generative AI product designed to enhance the coding experience for developers at all levels. It serves as a powerful tool for both experienced programmers seeking efficiency and newcomers looking to strengthen their coding skills.

Base Model

The foundation of StableCode is a comprehensive model that underwent initial training on a wide range of programming languages, sourced from the stack-dataset (v1.2) from BigCode. To refine its capabilities, the base model was further trained using popular languages such as Python, Go, Java, JavaScript, C, Markdown, and C++. This training involved a substantial dataset, comprising a staggering 560 billion tokens of code. This robust foundation equips StableCode with a deep understanding of various programming languages and structures.

Instruction Model

This model was meticulously fine-tuned for specific use cases, focusing on solving intricate programming challenges. By exposing it to around 120,000 pairs of code instruction and corresponding responses in Alpaca format, the instruction model has been sharpened to provide intelligent solutions for complex coding tasks.

Long-Context Window Model

StableCode introduces an advanced long-context window model that excels at generating single and multi-line autocomplete suggestions. Compared to previous open models with limited context windows, this new model is designed to handle significantly more code at once—approximately 2 to 4 times more. As a result, developers can effortlessly review or edit the equivalent of multiple average-sized Python files concurrently. This extended context window is particularly beneficial for those eager to expand their coding expertise and take on larger coding challenges.

Tutorial: Using StableCode for Code Completion

In this tutorial, we will learn how to use StableCode to generate code completion. We will go through each model and see how it works. We will also learn how to utilize StableCode in Google Colab and the Hugging Face Inference API, making it accessible even for those without powerful GPUs.

Implementation in Google Colab

Step 1 - Setting up the Project

Start by creating a new Notebook in Google Colab. Go to Google Colab, create a new Notebook, and name it StableCode Tutorial.

Step 2 - Install Required Packages

First, set the Runtime type to Python 3 and the Hardware accelerator to GPU. Then, install or update Python packages related to natural language processing (NLP) and machine learning:

• Click the Run button or CMD/CTRL + Enter to execute the single code cell.
• Wait until the installation is complete to proceed.

Step 3 - Using the StableCode Base Model

Now, let’s try the StableCode - Base Model:

• Add a new code cell.
• Click Run or CMD/CTRL + Enter.
• Wait for the model to load, which may take longer depending on your internet connection.
• Define a function to run the model. This function will take a prompt as input and return the result generated by StableCode.
• Add a new code cell and provide your desired prompt for completion.
• Click Run or CMD/CTRL + Enter to see the output.

Step 4 - Using the StableCode Instruction Model

Now let’s try the StableCode - Instruction Model:

• Change BASE_MODEL to INSTRUCTION_MODEL in the from_pretrained() function.
• Add a new code cell.
• Again, wait until the model is loaded, then provide your desired prompt for completion.

Step 5 - Using the StableCode Long Context Window Model

Finally, let's try the StableCode - Long Context Window Model:

• Change INSTRUCTION_MODEL to LONG_CONTEXT_WINDOW_MODEL in the from_pretrained() function.
• Add a new code cell and click Run or CMD/CTRL + Enter.

Implementation with Hugging Face Inference API

Alternatively, you can use the Hugging Face Inference API to run StableCode, which is convenient if you do not have a powerful GPU.

Step 1 - Create an Account in Hugging Face

Visit Hugging Face and create a new account or log in if you already have one.

Step 2 - Create a New Token

You need a token to access the Hugging Face Inference API:

• Go to your profile and click on Access tokens in the left sidebar.
• Click the New token button.
• Name your token, select read from the dropdown, and hit Generate a token.

Step 3 - Running StableCode with the Hugging Face Inference API

Go to the StableCode model page and click Deploy. From the dropdown, select Inference API, which will generate a code snippet for you to copy.

With this setup, you can effectively use StableCode without needing a high-end GPU.

Conclusion

Thank you for following along with this tutorial. If you have any questions, feel free to reach out on LinkedIn or Twitter; I'd love to hear from you!