Sketch让大模型输出更可控，一键实现各类任务的结构化应用。
Sketch: A Toolkit for Streamlining LLM Operations
- 提供多种任务模板和交互式流程，统一输出格式
- 开源数据集与基于LLaMA3-8B-Instruct的格式遵循模型
- 适合希望快速部署大模型应用的开发者与研究者
以GPT系列为代表的大语言模型在生成式方法上取得了显著成功，其灵活性使其能应对多种任务。然而，输出格式的不固定性给控制与利用模型输出带来了挑战，制约了其在各领域的应用。本文提出Sketch，一个面向多样化场景的LLM操作优化工具包。包含：（1）涵盖多种NLP任务的描述模板与提示词；（2）支持构建结构化输出服务的交互式流程；（3）用于输出格式控制的开源数据集及构建工具；（4）基于LLaMA3-8B-Instruct的开源模型，能准确理解并遵循格式指令。该工具包旨在为用户提供即插即用的便利，推动大模型在实际应用中的高效落地。相关组件将逐步开源至https://github.com/cofe-ai/Sketch。
原文摘要 · Abstract (English)
Large language models (LLMs) represented by GPT family have achieved remarkable success. The characteristics of LLMs lie in their ability to accommodate a wide range of tasks through a generative approach. However, the flexibility of their output format poses challenges in controlling and harnessing the model's outputs, thereby constraining the application of LLMs in various domains. In this work, we present Sketch, an innovative toolkit designed to streamline LLM operations across diverse fields. Sketch comprises the following components: (1) a suite of task description schemas and prompt templates encompassing various NLP tasks; (2) a user-friendly, interactive process for building structured output LLM services tailored to various NLP tasks; (3) an open-source dataset for output format control, along with tools for dataset construction; and (4) an open-source model based on LLaMA3-8B-Instruct that adeptly comprehends and adheres to output formatting instructions. We anticipate this initiative to bring considerable convenience to LLM users, achieving the goal of ''plug-and-play'' for various applications. The components of Sketch will be progressively open-sourced at https://github.com/cofe-ai/Sketch.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。