CodeGen
Open-source model for program synthesis
...Developed by Salesforce Research, the models are trained on large datasets containing both natural language and programming language content. This allows them to translate natural language descriptions into functional code across a variety of programming languages. CodeGen supports multi-turn program synthesis, meaning it can generate complex programs through a sequence of prompts that progressively refine the solution. The project also includes training infrastructure and model checkpoints that allow researchers to experiment with different model sizes and training configurations. Its architecture and training approach enable the models to perform competitively with proprietary coding models on benchmark tasks.