[OpenAI Codex] Evaluating Large Language Models Trained on Code
Linkofpaper:https://arxiv.org/abs/2107.03374.EvaluatingLargeLanguageModelsTrainedonCodeIntroductionCodexisaGPT-basedmodelfine-tunedonpubliccodefromGitHub,towritePythoncode.(Butcopilot,adistinctversion