On Thursday, August 24, Meta said it will release an artificial intelligence (AI) model to help you write code.
Code Llama, which will be free, can write code based on human text prompts. It’s also a tool that you can use for code completing and debugging, the social media giant said in a blog post.
Code Llama is built on top of Meta’s latest Llama 2 language model and will be available in different configurations, the company said, as it gears up to go head-to-head with Microsoft’s code-writing tool GitHub Copilot.
- Dubai AI and Web 3.0 Campus gives reason for Companies to Set Up in Dubai
- Saudi Arabia and UAE Invest Millions in Nvidia GPUs for AI Projects
- Tech Industry Giants Revamp Services to Meet EU’s Digital Services Act Requirements
Meta said that Code Llama supports popular coding languages like Python, C++, and Java and is not recommended for general text tasks.
There are two versions of Code Llama in development, with one specializing in Python, which is rightfully named Code Llama – Python. The other one, Code Llama – Instruct, uses natural language instructions and translates them into code.
Meta said Code Llama is state-of-the-art for publicly available large language models (LLMs) on coding tasks. You can think of it like ChatGPT, but it is specially built for coding to make the activity faster and more efficient.
The company also said Code Llama is part of its open approach to AI and is released under the same community license as Llama 2.
Meta has released a couple of AI models this year. Most are free and open-source, including Llama 2, a similar model to OpenAI’s ChatGPT and Google’s Bard.