We introduce API Pack, a multilingual dataset featuring over one million instruction-API call pairs aimed at advancing large language models' API call generation capabilities. Through experiments, we demonstrate API Pack's efficacy in enhancing models for this specialized task while maintaining their overall proficiency at general coding. Fine-tuning CodeLlama-13B on just 20,000 Python instances yields over 10% and 5% higher accuracy than GPT-3.5 and GPT-4 respectively in generating unseen API calls. Scaling to 100k examples improves generalization to new APIs not seen during training. In addition, cross-lingual API call generation is achieved without needing extensive data per language. The dataset, fine-tuned models, and overall code base are publicly available at https://github.com/anonymous_url.

翻译：我们提出API Pack这一多语言数据集，包含超过一百万条指令-API调用对，旨在提升大语言模型的API调用生成能力。实验表明，API Pack在增强模型特定任务能力的同时，能保持其通用编码水平的整体熟练度。仅使用2万条Python实例微调CodeLlama-13B，在生成未见API调用时准确率分别比GPT-3.5和GPT-4高10%和5%以上。将规模扩展至10万条示例后，模型对训练中未出现的新API的泛化能力进一步提升。此外，无需为每种语言准备大量数据即可实现跨语言API调用生成。该数据集、微调模型及完整代码库已开源发布于https://github.com/anonymous_url。