A family of code models ranging from 3B to 34B trained on 3.5-4.5T tokens of code written in 116 programming languages.

Open code models based on Gemma models by further training on over 500 billion tokens of primarily code

A diffusion code generation model that iteratively refines entire programs based on encoded natural language, overcoming the limitation of auto-regressive models in code generation by allowing reconsideration of earlier tokens.

LLaMA 2 based LLM for code.

Proposes an approach to make the training of LLMs for program synthesis more efficient by unifying key components of model architectures, learning methods, infill sampling, and data distributions

An LLM trained for program synthesis using input-output examples and natural language descriptions.

A GPT language model finetuned on publicly available code from GitHub.