metadata

license: apache-2.0
task_categories:
  - text-generation
language:
  - en
tags:
  - code
pretty_name: Tool-Calling Instruction Dataset
size_categories:
  - n<1K

🛠️ Tool-Calling Instruction Dataset

This dataset consists of instruction-completion pairs for training Large Language Models (LLMs) to convert natural language requests into structured tool/function calls.
The data format is inspired by ChatML and includes explicit system, user, and assistant roles.

Dataset Structure

Each example is a single JSON object with a text field, containing a chat-formatted prompt and response.
The user gives an instruction (e.g., "Analyze the file ...").
The assistant responds with a tool/function call (e.g., TOOL_NEEDED: ... PARAMS: {...}).

Sample row:

{
  "text": "<|im_start|>system\nBelow are some instructions that describe some tasks. Write responses that appropriately complete each request.<|im_end|>\n<|im_start|>user\nAnalyze the file C:/Users/emre/Desktop/abc.tif<|im_end|>\n<|im_start|>assistant\nTOOL_NEEDED: analyze_tiff\nPARAMS: {\"filepath\": \"C:/Users/emre/Desktop/abc.tif\"}<|im_end|>"
}