Flacuna：利用FLAN Fine-Tuning释放维昆纳的问题解决能力

Flacuna: Unleashing the Problem Solving Power of Vicuna using FLAN Fine-Tuning

July 5, 2023

作者: Deepanway Ghosal, Yew Ken Chia, Navonil Majumder, Soujanya Poria

cs.AI

摘要

最近，INSTRUCTEVAL的发布为利用编码器-解码器或仅解码器架构的大型语言模型（LLMs）的性能提供了宝贵的见解。有趣的是，尽管四年前推出，基于T5的LLMs（如FLAN-T5）在需要一般问题解决技能的任务上仍然优于最新的基于解码器的LLMs（如LLAMA和VICUNA）。这种性能差异可以归因于三个关键因素：（1）预训练数据，（2）骨干架构和（3）指令数据集。在这份技术报告中，我们的主要重点是通过利用基于LLAMA的大型语言模型VICUNA来调查第三个因素的影响，该模型已在ChatGPT对话上进行了微调。为实现这一目标，我们使用名为FLANMINI的自定义指令数据集收集对VICUNA进行了微调。该数据集包括众所周知的大规模指令数据集FLAN的子集，以及从ChatGPT/GPT-4衍生的各种与代码相关的数据集和对话数据集。该数据集包含大量需要解决问题技能的任务。我们的实验结果明显表明，我们的模型FLACUNA的增强问题解决能力是通过在FLAN数据集上微调VICUNA获得的，从而在INSTRUCTEVAL的众多基准数据集上取得了显著改进。FLACUNA可在https://huggingface.co/declare-lab/flacuna-13b-v1.0 公开获取。

English

Recently, the release of INSTRUCTEVAL has provided valuable insights into the performance of large language models (LLMs) that utilize encoder-decoder or decoder-only architecture. Interestingly, despite being introduced four years ago, T5-based LLMs, such as FLAN-T5, continue to outperform the latest decoder-based LLMs, such as LLAMA and VICUNA, on tasks that require general problem-solving skills. This performance discrepancy can be attributed to three key factors: (1) Pre-training data, (2) Backbone architecture, and (3) Instruction dataset. In this technical report, our main focus is on investigating the impact of the third factor by leveraging VICUNA, a large language model based on LLAMA, which has undergone fine-tuning on ChatGPT conversations. To achieve this objective, we fine-tuned VICUNA using a customized instruction dataset collection called FLANMINI. This collection includes a subset of the large-scale instruction dataset known as FLAN, as well as various code-related datasets and conversational datasets derived from ChatGPT/GPT-4. This dataset comprises a large number of tasks that demand problem-solving skills. Our experimental findings strongly indicate that the enhanced problem-solving abilities of our model, FLACUNA, are obtained through fine-tuning VICUNA on the FLAN dataset, leading to significant improvements across numerous benchmark datasets in INSTRUCTEVAL. FLACUNA is publicly available at https://huggingface.co/declare-lab/flacuna-13b-v1.0.