open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-19 12:58:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into rich/graphcolor

Browse source
This commit is contained in:
Andreas Köpf 2025-02-14 07:09:38 +01:00 • committed by GitHub
commit b64d0af2bc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 385 additions and 61 deletions
Download patch file Download diff file Expand all files Collapse all files

1
reasoning_gym/algorithmic/__init__.py
View file

@ -26,7 +26,6 @@ from .rotate_matrix import RotateMatrixConfig, RotateMatrixDataset
from .sentence_reordering import SentenceReorderingConfig, SentenceReorderingDataset
from .spell_backward import SpellBackwardConfig, SpellBackwardDataset
from .spiral_matrix import SpiralMatrixConfig, SpiralMatrixDataset
from .string_insertion import StringInsertionConfig, StringInsertionDataset
from .string_manipulation import StringManipulationConfig, StringManipulationDataset
from .word_ladder import WordLadderConfig, WordLadderDataset
from .word_sequence_reversal import WordSequenceReversalConfig, WordSequenceReversalDataset

8
reasoning_gym/algorithmic/number_sorting.py
View file

@ -34,6 +34,11 @@ class NumberSortingDataset(ProceduralDataset):
def __init__(self, config: NumberSortingConfig):
super().__init__(config=config, seed=config.seed, size=config.size)
self.added_instruction = """
Please follow the instruction below:
## 1. Let all your answers be a list of numbers. Instead of reporting your answer as -69, -13, 1, 7, 11, 43, 59, 61, use ['-69', '-13', '1', '7', '11', '43', '59', '61'] instead
## 2. Convert all numbers in the square brackets as strings. For example, ['-69', '-13', '1', '7', '11', '43', '59', '61']
"""
def _format_number(self, num: float, decimals: int) -> str:
"""Format number with specified decimal places"""
@ -78,9 +83,10 @@ class NumberSortingDataset(ProceduralDataset):
is_ascending = rng.choice([True, False])
direction = "ascending" if is_ascending else "descending"
answer = asc_answer if is_ascending else desc_answer
question = f"Sort these numbers in {direction} order: {', '.join(number_strs)}" + self.added_instruction
return {
"question": f"Sort these numbers in {direction} order: {', '.join(number_strs)}",
"question": question,
"answer": str(answer),
"metadata": {"original_numbers": number_strs, "direction": direction, "sorted_numbers": answer},
}