Code Llama vs. Imaginary Programming vs. Python vs. StarCoder Comparison Chart

Imaginary Programming lets you use OpenAI's GPT engine as a runtime to accomplish things you've never been able to do before in your code. All you do is define a function prototype in TypeScript (without an implementation!), and Imaginary Programming uses GPT to take care of the rest. Use Imaginary programming for any task where human-like intelligence around text is needed. You can install imaginary programming into your current JavaScript and TypeScript projects, or you can try the online Playground to experiment with Imaginary Programming.

StarCoder and StarCoderBase are Large Language Models for Code (Code LLMs) trained on permissively licensed data from GitHub, including from 80+ programming languages, Git commits, GitHub issues, and Jupyter notebooks. Similar to LLaMA, we trained a ~15B parameter model for 1 trillion tokens. We fine-tuned StarCoderBase model for 35B Python tokens, resulting in a new model that we call StarCoder. We found that StarCoderBase outperforms existing open Code LLMs on popular programming benchmarks and matches or surpasses closed models such as code-cushman-001 from OpenAI (the original Codex model that powered early versions of GitHub Copilot). With a context length of over 8,000 tokens, the StarCoder models can process more input than any other open LLM, enabling a wide range of interesting applications. For example, by prompting the StarCoder models with a series of dialogues, we enabled them to act as a technical assistant.