@article{opencodeinstructalargescaleinstruction, title = {OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs}, author = {Wasi Uddin Ahmad and Aleksander Ficek and Mehrzad Samadi and Jocelyn Huang and Vahid Noroozi and Somshubra Majumdar and Boris Ginsburg}, year = {2025}, eprint = {2504.04030}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.04030v1}, }