Files
trl/scripts/generate_toolcall_dataset.py
Quentin Gallouédec c262674ea7 🧰 [SFT] Tool support (#3597)
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
2025-06-20 17:39:24 +02:00

235 lines
9.5 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Copyright 2020-2025 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from dataclasses import dataclass, field
from datasets import Dataset
from transformers import HfArgumentParser
from transformers.utils import get_json_schema
@dataclass
class ScriptArguments:
r"""
Arguments for the script.
Args:
test_size (`float`, *optional*, defaults to `0.1`):
Fraction of the dataset to include in the test split.
push_to_hub (`bool`, *optional*, defaults to `False`):
Whether to push the dataset to the Hugging Face Hub.
repo_id (`str`, *optional*, defaults to `"trl-internal-testing/zen"`):
Hugging Face repository ID to push the dataset to.
"""
test_size: float = field(
default=0.1,
metadata={"help": "Fraction of the dataset to include in the test split."},
)
push_to_hub: bool = field(
default=False,
metadata={"help": "Whether to push the dataset to the Hugging Face Hub."},
)
repo_id: str = field(
default="trl-internal-testing/toolcall",
metadata={"help": "Hugging Face repository ID to push the dataset to."},
)
def main(test_size, push_to_hub, repo_id):
# Fictitious functions to simulate tool calls
def start_timer(duration: int) -> int:
"""
Starts a timer for the specified duration in seconds.
Args:
duration: Duration in seconds to set the timer for.
Returns:
The duration set for the timer.
"""
return duration
def get_current_time(location: str) -> str:
"""
Returns the current time in the specified location.
Args:
location: The location for which to get the current time.
Returns:
The current time in the specified location.
"""
return "06:22:48"
def get_air_quality_index(location: str) -> int:
"""
Returns the air quality index for the specified location.
Args:
location: The location for which to get the air quality index.
Returns:
The air quality index for the specified location.
"""
return 53
def play_music(title: str, artist: str) -> dict:
"""
Plays music by the specified title and artist.
Args:
title: The title of the music to play.
artist: The artist of the music to play.
Returns:
A dictionary indicating the status of the music playback.
"""
return {"status": "Playing"}
def get_weather_forecast(city: str, date: str) -> dict:
"""
Returns the weather forecast for the specified city and date.
Args:
city: The city for which to get the weather forecast.
date: The date for which to get the weather forecast.
Returns:
A dictionary containing the temperature and weather condition.
"""
return {"temperature": 22, "condition": "partly cloudy"}
def control_light(room: str, state: str) -> dict:
"""
Controls the light in the specified room.
Args:
room: The room where the light should be controlled.
state: The desired state of the light ("on" or "off").
Returns:
A dictionary indicating the state of the light.
"""
return {"state": state}
def create_reminder(time: str, note: str) -> str:
"""
Creates a reminder for the specified time and note.
Args:
time: The time for the reminder.
note: The note for the reminder.
Returns:
A confirmation message indicating that the reminder has been set.
"""
return "I'll remind you to call mom at 7 PM."
def get_wind_conditions(city: str, unit: str) -> tuple[int, str]:
"""
Returns the wind conditions for the specified city.
Args:
city: The city for which to get the wind conditions.
unit: The unit of measurement for the wind speed (e.g., "mph").
Returns:
A tuple containing the wind speed and direction.
"""
return 14, "NW"
start_timer = get_json_schema(start_timer)
get_current_time = get_json_schema(get_current_time)
get_air_quality_index = get_json_schema(get_air_quality_index)
play_music = get_json_schema(play_music)
get_weather_forecast = get_json_schema(get_weather_forecast)
control_light = get_json_schema(control_light)
create_reminder = get_json_schema(create_reminder)
get_wind_conditions = get_json_schema(get_wind_conditions)
# fmt: off
dataset = Dataset.from_dict({
"messages": [
[
{"role": "user", "content": "Set a timer for 10 minutes."},
{"role": "assistant", "tool_calls": [{"type": "function", "function": {"name": "start_timer", "arguments": {"duration": 600}}}]},
{"role": "tool", "name": "start_timer", "content": "600"},
{"role": "assistant", "content": "Timer set for 10 minutes."},
],
[
{"role": "user", "content": "What time is it in Tokyo?"},
{"role": "assistant", "tool_calls": [{"type": "function", "function": {"name": "get_current_time", "arguments": {"location": "Tokyo"}}}]},
{"role": "tool", "name": "get_current_time", "content": "06:22:48"},
{"role": "assistant", "content": "The current time in Tokyo is 06:22 AM."},
],
[
{"role": "user", "content": "Is the air clean today in Lisbon?"},
{"role": "assistant", "tool_calls": [{"type": "function", "function": {"name": "get_air_quality", "arguments": {"location": "Lisbon, Portugal"}}}]},
{"role": "tool", "name": "get_air_quality", "content": "53"},
{"role": "assistant", "content": "The air quality is moderate."},
],
[
{"role": "user", "content": "Play some music."},
{"role": "assistant", "tool_calls": [{"type": "function", "function": {"name": "play_music", "arguments": {"title": "Take Five", "artist": "Dave Brubeck"}}}]},
{"role": "tool", "name": "play_music", "content": "{'status': 'Playing'}"},
{"role": "assistant", "content": "Enjoy the jazz tunes!"},
],
[
{"role": "user", "content": "What's the weather like tomorrow in Berlin?"},
{"role": "assistant", "tool_calls": [{"type": "function", "function": {"name": "get_weather_forecast", "arguments": {"city": "Berlin", "date": "2025-06-16"}}}]},
{"role": "tool", "name": "get_weather_forecast", "content": "{'temperature': 22, 'condition': 'partly cloudy'}"},
{"role": "assistant", "content": "Tomorrow in Berlin will be partly cloudy with a high of 22°C."}
],
[
{"role": "user", "content": "Turn on the living room lights."},
{"role": "assistant", "tool_calls": [{"type": "function", "function": {"name": "control_light", "arguments": {"room": "living room", "state": "on"}}}]},
{"role": "tool", "name": "control_light", "content": "{'state': 'on'}"},
{"role": "assistant", "content": "The living room lights are now on."}
],
[
{"role": "user", "content": "Remind me to call mom at 7 PM."},
{"role": "assistant", "tool_calls": [{"type": "function", "function": {"name": "create_reminder", "arguments": {"time": "19:00", "note": "Call mom"}}}]},
{"role": "tool", "name": "create_reminder", "content": "Reminder set"},
{"role": "assistant", "content": "Okay, Ill remind you to call mom at 7 PM."}
],
[
{"role": "user", "content": "How strong is the wind in Chicago right now?"},
{"role": "assistant", "tool_calls": [{"type": "function", "function": {"name": "get_wind_conditions", "arguments": {"city": "Chicago", "unit": "mph"}}}]},
{"role": "tool", "name": "get_wind_conditions", "content": "(14, 'NW')"},
{"role": "assistant", "content": "The wind in Chicago is blowing at 14 mph from the northwest."}
]
],
"tools": [
[start_timer, create_reminder],
[get_current_time],
[get_air_quality_index, get_weather_forecast, get_wind_conditions],
[play_music, control_light],
[get_weather_forecast, get_wind_conditions],
[control_light],
[start_timer, create_reminder],
[get_weather_forecast, get_wind_conditions],
]
})
dataset = dataset.train_test_split(test_size=test_size, shuffle=False)
if push_to_hub:
dataset.push_to_hub(repo_id)
# fmt: on
if __name__ == "__main__":
parser = HfArgumentParser(ScriptArguments)
script_args = parser.parse_args_into_dataclasses()[0]
main(script_args.test_size, script_args.push_to_hub, script_args.repo_id)