The project provides code language models pre-trained on project-level code corpus with a 16K window size and fill-in-the-blank tasks to support code synthesis and project-level completion. Models range from 1B to 33B parameters and are available via HuggingFace. It achieves state-of-the-art performance among open-source code models on benchmarks including HumanEval, MultiPL-E, MBPP, DS-1000, and APPS.