Meta has released a tool called Code Llama, built on top of its Llama 2 large language model, to generate new code and debug human-written work, the company said.
Code Llama will use the same community license as Llama 2 and is free for research and commercial use.
Code Llama, Meta said, can create strings of code from prompts or complete and debug code when pointed to a specific code string. In addition to the base Code Llama model, Meta released a Python-specialized version called Code Llama-Python and another version called Code Llama-Instrct, which can understand instructions in natural language. According to Meta, each specific version of Code Llama is not interchangeable, and the company does not recommend the base Code Llama or Code Llama-Python for natural language instructions.
“Programmers are already using LLMs to assist in a variety of tasks, ranging from writing new software to debugging existing code,” Meta said in a blog post. “The goal is to make developer workflows more efficient so they can focus on the most human-centric aspects of their jobs.”
Meta claims Code Llama performed better than publicly available LLMs based on benchmark testing but did not specifically name which models it tested against. The company said Code Llama scored 53.7 percent on the code benchmark HumanEval and was able to accurately write code based on a text description.
Meta will release three sizes of Code Llama and said its smallest size fits on a single GPU for more low-latency projects.
Code generators have been helping developers work for a while now. GitHub launched Copilot in March, powered by OpenAI’s GPT-4, to quickly write and check code. GitHub Copilot can also rewrite old code to update it. Amazon’s AWS also has CodeWhisperer, which also writes, checks, and updates code. And yes, Google also has a code-writing tool in AlphaCode, but that isn’t out yet.
GitHub’s parent company, Microsoft, and OpenAI are being sued for allegedly violating copyright law with Copilot because the tool can reproduce licensed code.