Meta has announced a new large language model (LLM) that can use text prompts to generate and discuss code. Called Code Llama, the tool is meant for publicly available LLMs on coding tasks. “It has the potential to make workflows faster and more efficient for developers and lower the barrier to entry for people who are learning to code,” said Meta in a blog post. Further, the company said that Code Llama has the potential to be used as a productivity and educational tool to help programmers write more robust, well-documented software.

What can Code Llama do?

According to Meta, the model features enhanced coding capabilities and can generate code and natural language about code, from both code and natural language prompts . For instance, users can say “Write me a function that outputs the fibonacci sequence” and Code Llama will generate code on that basis. Furthermore, it can also be used for code completion and debugging. It supports many of the most popular programming languages used today, including Python, C++, Java, PHP, Typescript (Javascript), C#, Bash and more.
With the new model, Meta is taking an aim at ChatGPT, which has reportedly become quite popular among coders. Github also has a OpenAI-powered coding tool whereas Amazon too has a similar model that helps people write code. There are reports about Google also working on a code writing AI tool.
Meta said that programmers are already using LLMs to assist in a variety of tasks. “The goal is to make developer workflows more efficient so that they can focus on the most human-centric aspects of their job, rather than repetitive tasks,” the company said.
Like its other AI tools and models, Meta has made Code Llama also open source and made available to everyone. “We believe that AI models, and LLMs for coding in particular, benefit most from an open approach, both in terms of innovation and safety,” said Meta.