Zafir Stojanovski
a48ff14507
add difficulty where possible ( #274 )
2025-03-07 19:01:26 +01:00
Andreas Köpf
c2263979bc
Basic curriculum ( #198 )
...
* feat: Add optional curriculum support to dataset registration and creation
* docs: Add docstrings to create_curriculum() and register_dataset()
* feat: Add curriculum configuration classes for CurriculumExperiment
* feat: Add weight parameter to CurriculumAttributeConfig and use in DatasetSpec
* refactor: Simplify CurriculumAttributeConfig with "*" attribute level support
* test: Add unit tests for CurriculumExperiment class
* feat: Add from_yaml() method to CurriculumExperimentConfig with unit test
2025-03-07 11:22:12 +01:00
joesharratt1229
1893691c57
updated algorithmics dataset ( #269 )
...
* updated algorithmic datasets
* added changes to symbolic and power
* updated power function test
2025-03-05 23:32:53 +01:00
Zafir Stojanovski
3d9bb382aa
feat(env): Count Bits Curriculum ( #267 )
...
* add min n
* count bits
2025-03-05 22:44:04 +01:00
Andreas Köpf
b2904ccab9
Minor question template & score_answer improvements ( #261 )
...
* math prompt improvements
* ignore brackets in complex_arithmetic results
* improve additional instruction in prompt of polynomial_equations
* more strict tests for score_answer in polynomial_equations
* simplify special reward handling
* fix test_intermediate_integration
* fix sokoban dataset
* add common dataset score_answer consistency test
2025-03-04 21:55:09 +01:00
Andreas Köpf
07388767a2
Reduce precision from 28 to 6 in DecimalArithmeticDataset ( #256 )
2025-03-03 21:57:08 +01:00
Zafir Stojanovski
2f9d94c1e7
fix: Unify Prompts ( #254 )
...
* remove cot
* fix prompt template
* fix pool matrix
* spiral matrix fixed
2025-03-03 21:55:53 +01:00
Andreas Köpf
ece6990709
Remove strip from ProceduralDataset::core score_answer() ( #250 )
...
* remove strip from ProceduralDataset::core score_answer(), strip in extract answer (optional, default=True)
* test: Move test_extract_answer() from test_dataset.py to test_utils.py
* refactor: Improve decimal reward computation with more flexible comparison
* fix: Implement rounding for format_number when round_if_needed is True
* test: Add test case for compute_decimal_reward with sign and zeros
2025-03-02 08:46:36 +01:00
Rich Jones
a1b1272e8d
sm fixes
2025-02-27 11:54:04 +01:00
vncntt
465db5c5c7
Add KnightsKnavesDataset (knights_knaves)
...
Adapted code from https://github.com/AlphaPav/mem-kk-logic/blob/main/data_prep/lib_kk.py
---------
Co-authored-by: Andreas Koepf (aider) <andreas.koepf@provisio.com>
2025-02-25 20:15:38 +01:00
Andreas Koepf
74f590e24f
more native type hints
2025-02-21 21:23:14 +01:00
Andreas Köpf
82839dec96
Merge pull request #181 from open-thought/rich/bitwise
...
Add Bitwise Arithmetic
2025-02-21 17:27:45 +01:00
Andreas Koepf (aider)
5f9d5c0e0f
docs: Add comment explaining automatic base detection in int() conversion
2025-02-21 17:16:11 +01:00
Andreas Koepf (aider)
196d236978
docs: Add detailed comments for BitwiseArithmeticConfig and BitwiseArithmeticDataset
2025-02-21 17:14:00 +01:00
Andreas Koepf
aa37fbc2cf
refactor: Update type hints and remove unused imports in bitwise_arithmetic.py
2025-02-21 17:13:36 +01:00
Andreas Koepf (aider)
253fd55a00
feat: Add typing hints and improve difficulty parameter documentation in bitwise_arithmetic.py
2025-02-21 17:11:40 +01:00
Rich Jones
aaff230dff
lint
2025-02-21 17:09:19 +01:00
Rich Jones
217771a1b0
ensure arbitrary bit depth and signed values
2025-02-21 16:52:26 +01:00
Andreas Koepf
476e37e70b
use Decimal class for numeric comparison e.g. +0123.100 == 123.1
2025-02-21 15:36:06 +01:00
Andreas Koepf
ff5b210106
use native types List->list, Dict->dict, Set->set, Tuple->tuple
2025-02-21 15:15:38 +01:00
AhmedSaif2
6b5c7a8637
add a helper function to handle redundant code
2025-02-21 15:54:00 +02:00
Rich Jones
b9ab1cb2ae
clean up comments
2025-02-21 12:17:21 +01:00
Rich Jones
cc451adb17
add to init
2025-02-21 12:07:17 +01:00
Rich Jones
1733927ed9
add bitwise arithmetic
2025-02-21 12:02:41 +01:00
AhmedSaif2
27c597c10a
remove added instructions
2025-02-20 21:29:01 +02:00
AhmedSaif2
1da1909666
Add score answer to support comma format
2025-02-20 20:52:31 +02:00
Andreas Köpf
3adf5b6c22
Merge pull request #158 from open-thought/rich/decimalmath
...
Decimal Arithmetic
2025-02-20 12:35:41 +01:00
Rich Jones
58d261be98
lint
2025-02-20 12:29:12 +01:00
Rich Jones
921c9b1d7b
type hints
...
blind roboting
2025-02-20 12:10:28 +01:00
ahmedsaif
df4bb0b897
Add allow-negation in products dataset
2025-02-20 12:01:09 +02:00
Rich Jones
e8691d74a1
add to init
2025-02-20 10:51:00 +01:00
Rich Jones
16d96e6af1
Merge branch 'rich/decimalmath' of github.com:open-thought/reasoning-gym into rich/decimalmath
2025-02-20 10:46:13 +01:00
Rich Jones
eb64e3a2b8
add random paren grouping
2025-02-20 10:46:01 +01:00
Rich Jones
772ca584b5
Merge branch 'main' into rich/decimalmath
2025-02-20 10:07:28 +01:00
vncntt
8423aba33f
Merge branch 'open-thought:main' into decimal_chain_sum
2025-02-19 15:31:20 -08:00
vncntt
b94c385c46
register decimal_chain_sum
2025-02-19 15:30:30 -08:00
Andreas Köpf
3cd0fd9019
Merge pull request #164 from vncntt/decimal_chain_sum
...
decimal_chain_sum
2025-02-20 00:14:23 +01:00
vncntt
36ca729824
decimal refactor
2025-02-19 14:46:27 -08:00
Rich Jones
a76e56fccc
implement decimal precision
2025-02-19 12:30:07 +01:00
Zafir Stojanovski
fec058d905
number format
2025-02-19 11:41:06 +01:00
vncntt
0420dfe433
decimal_chain_sum
2025-02-19 01:51:10 -08:00
Andreas Koepf
e9a2097a71
remove redundant assert in ChainSumConfig.validate()
2025-02-19 09:42:32 +01:00
Rich Jones
0cd2eb50d7
Merge branch 'rich/decimalmath' of github.com:open-thought/reasoning-gym into rich/decimalmath
2025-02-19 03:34:57 +01:00
Rich Jones
c3bc7937dc
[wip] more flexible api
2025-02-19 03:29:40 +01:00
Rich Jones
36b2bceda3
Merge branch 'main' into rich/decimalmath
2025-02-18 20:53:36 +01:00
Rich Jones
bd56a7b1fe
lint
2025-02-18 19:22:03 +01:00
Rich Jones
e2bdfb4c1c
decimal math
2025-02-18 19:20:33 +01:00
Andreas Koepf
aa794253fe
minor formatting changes
2025-02-17 18:20:18 +01:00
abdulhakeem
5b1e42f878
Tweaked some question templates
2025-02-17 02:58:42 -06:00
Andreas Koepf
99b49f868f
fix question templates
2025-02-16 23:04:24 +01:00
