ToolQA

by night-chen · Agent Tool · ★ 286

About ToolQA

🛠️ToolQA 🛠️ The official repository for code and data of ToolQA dataset. ToolQA is a open-source dataset specifically designed for evaluations on tool-augmented large language models (LLMs). This repo provides the dataset, the corresponding data generation code, and the implementations of baselines on our dataset. Features Our questions are selected and guaranteed that LLMs have little chance to memorize and answer correctly within their internal knowledge; The majority of the questions in ToolQA require compositional use of multiple tools.

large-language-modelsnatural-language-understandingnatural-lauguage-processingquestion-answeringtools

Quick Facts

Stars286
Forks14
LanguageJupyter Notebook
CategoryAgent Tool
LicenseApache-2.0
Quality Score67.6839033158702/100
Open Issues5
Last Updated2023-08-19
Created2023-06-06
Est. Tokens~24k

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Jupyter Notebook Agent Tools

Frequently Asked Questions

What is ToolQA?

ToolQA is ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.. It is categorized as a Agent Tool with 286 GitHub stars.

What programming language is ToolQA written in?

ToolQA is primarily written in Jupyter Notebook. It covers topics such as large-language-models, natural-language-understanding, natural-lauguage-processing.

How do I install or use ToolQA?

You can find installation instructions and usage details in the ToolQA GitHub repository at github.com/night-chen/ToolQA. The project has 286 stars and 14 forks, indicating an active community.

What license does ToolQA use?

ToolQA is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

View on GitHub → Browse Agent Tool tools