Code Llama is a powerful, open-source suite of large language models specifically fine‑tuned for code-related tasks. Built atop Meta’s foundational Llama 2 models, it offers variants at 7B, 13B, 34B, and 70B parameters—each optimized with 500 billion code tokens and extended context windows up to 100 k tokens
Code Llama
Meta's open-source code model, built on Llama 2 for code generation and infilling. The repository was archived in July 2025 and is no longer maintained, superseded by newer Llama model generations.
Reviews
- No reviews yet.
See something outdated? Suggest an update