Meta AI Open Sources Code Llama: A SOTA Code-Specialized Llama 2

In a new paper Code Llama: Open Foundation Models for Code, a Meta AI research team releases Code Llama, a family of code-specialized Llama 2 models for code generation and infilling, which achieves state-of-the-art performance against open models on code benchmarks.

ai ai research art artificial intelligence benchmarks code code generation code llama deep-neural-networks family foundation large language model llama llama 2 machine learning machine learning & data science meta meta ai meta ai research ml nature language tech paper performance releases research research team sota state team technology