In this technical report, we present three novel datasets of Kotlin code:
KStack, KStack-clean, and KExercises. We also describe the results of
fine-tuning CodeLlama and DeepSeek models on this data. Additionally, we
present a version of the HumanEval benchmark rewritten by human experts into
Kotlin - both the solutions and the tests. Our results demonstrate that small,
high-quality datasets (KStack-clean and KExercises) can significantly improve
model performance on code generation tasks, achieving up to a 16-point increase
in pass rate on the HumanEval benchmark. Lastly, we discuss potential future
work in the field of improving language modeling for Kotlin, including the use
of static analysis tools in the learning process and the introduction of more
intricate and realistic benchmarks.

我们介绍了三个新的 Kotlin 代码数据集，KStack，KStack-clean 和 KExercises。我们描述了在这些数据上对 CodeLlama 和 DeepSeek 模型的微调结果。我们还展示了人工专家将 HumanEval 基准测试改写为 Kotlin 的版本，包括解决方案和测试。我们的结果表明，小而高质量的数据集（KStack-clean 和 KExercises）可以显着提高模型在代码生成任务上的性能，在 HumanEval 基准测试中通过率提高了最多 16 个百分点。最后，我们讨论了改进 Kotlin 语言建模的潜在未来工作，包括在学习过程中使用静态分析工具和引入更复杂、更实际的基准测试。