WaveCoder：具廣泛且多功能性的增強指令調整，搭配精煉的資料生成

WaveCoder: Widespread And Versatile Enhanced Instruction Tuning with Refined Data Generation

December 20, 2023

作者: Zhaojian Yu, Xin Zhang, Ning Shang, Yangyu Huang, Can Xu, Yishujie Zhao, Wenxiang Hu, Qiufeng Yin

cs.AI

摘要

最近的研究表明，在對高質量指令數據集進行微調後，所得到的模型能夠具有令人印象深刻的能力，以應對各種任務。然而，現有的指令數據生成方法通常會產生重複數據，並且在數據質量上不夠可控。本文通過將指令數據分類為4個與代碼相關的任務，擴展了指令微調的泛化能力，並提出了基於LLM的生成器-鑑別器數據處理框架，從開源代碼中生成多樣且高質量的指令數據。因此，我們介紹了CodeOcean，這是一個包含20,000個指令實例的數據集，涵蓋了4個通用的與代碼相關的任務，旨在增強指令微調的效果並提高微調模型的泛化能力。隨後，我們提出了WaveCoder，這是一個經過微調的代碼LLM，具有廣泛且多功能的增強指令微調。該模型專為增強代碼語言模型（LLMs）的指令微調而設計。我們的實驗表明，Wavecoder模型在相同微調規模下在不同與代碼相關的任務上的泛化能力優於其他開源模型。此外，Wavecoder在以前的代碼生成任務中表現出高效性。因此，本文對指令數據生成和微調模型領域做出了重要貢獻，為增強代碼相關任務中的性能提供了新的見解和工具。

English

Recent work demonstrates that, after being fine-tuned on a high-quality instruction dataset, the resulting model can obtain impressive capabilities to address a wide range of tasks. However, existing methods for instruction data generation often produce duplicate data and are not controllable enough on data quality. In this paper, we extend the generalization of instruction tuning by classifying the instruction data to 4 code-related tasks and propose a LLM-based Generator-Discriminator data process framework to generate diverse, high-quality instruction data from open source code. Hence, we introduce CodeOcean, a dataset comprising 20,000 instruction instances across 4 universal code-related tasks,which is aimed at augmenting the effectiveness of instruction tuning and improving the generalization ability of fine-tuned model. Subsequently, we present WaveCoder, a fine-tuned Code LLM with Widespread And Versatile Enhanced instruction tuning. This model is specifically designed for enhancing instruction tuning of Code Language Models (LLMs). Our experiments demonstrate that Wavecoder models outperform other open-source models in terms of generalization ability across different code-related tasks at the same level of fine-tuning scale. Moreover, Wavecoder exhibits high efficiency in previous code generation tasks. This paper thus offers a significant contribution to the field of instruction data generation and fine-tuning models, providing new insights and tools for enhancing performance in code-related tasks.