Commit graph

1189 commits

Author SHA1 Message Date
Andreas Köpf
c8e77d21a7
fix: Improve error logging and preserve full model response in eval process (#337) 2025-03-12 00:01:49 +01:00
joesharratt1229
be75c3aa5f
added intermediate integration (#334) 2025-03-11 23:57:51 +01:00
Zafir Stojanovski
aa6ccf1946
number filtering curriculum (#333) 2025-03-11 23:56:06 +01:00
Oliver Stanley
f14662e213
Add a few new CodeI/O samples, resolve numeric answer scoring bug (#332)
* add handful of codeio samples

* scoring fix
2025-03-11 23:55:33 +01:00
vncntt
c3c6cc8051
gcd curriculum (#331) 2025-03-11 08:25:24 +01:00
Rich Jones
126eecc798
fix dice (#330) 2025-03-11 08:24:32 +01:00
Andreas Koepf
770255b608 fix pre-commit 2025-03-11 08:18:55 +01:00
joesharratt1229
b497e35fb8
added self reference curr (#329) 2025-03-11 00:23:26 +01:00
joesharratt1229
54074b17ef
Added zebra curriculum (#328)
* added zebra curriculum

* added metadata
2025-03-11 00:22:54 +01:00
Zafir Stojanovski
f204a848d9
spell backward curriculum (#327)
Co-authored-by: Andreas Köpf <andreas.koepf@xamla.com>
2025-03-11 00:22:28 +01:00
Zafir Stojanovski
a23c8c3d4e
sentence reordering curriculum (#326) 2025-03-11 00:21:41 +01:00
joesharratt1229
3c39cbda40
added sokoban dataset (#325) 2025-03-11 00:21:03 +01:00
joesharratt1229
91b3347d53
added quantum lock curriculum (#324) 2025-03-11 00:20:24 +01:00
joesharratt1229
e9944149bd
added tsumego curric (#323) 2025-03-11 00:19:55 +01:00
Zafir Stojanovski
9aeef4ebb0
palindrome generation curriculum (#322) 2025-03-11 00:19:11 +01:00
Zafir Stojanovski
ad48c551f9
feat(env): Number Sorting Curriculum (#321)
* number sorting curriculum

* metadata
2025-03-11 00:18:20 +01:00
joesharratt1229
105374183f
Algebra/curr (#320)
* add polynomial equation curriculum

* added simple integration

* addded metadata to config
2025-03-11 00:17:07 +01:00
Zafir Stojanovski
0bce1a6ae1
feat(env): Letter Jumble Curriculum (#319)
* base curriculum

* tests
2025-03-11 00:16:05 +01:00
Rich Jones
2b8f21c502
Correct Graph Coloring Difficulty (#318)
* correct gcolor difficulty

* refactor test
2025-03-11 00:14:38 +01:00
Rich Jones
d9ef4f4d14
Fix GoL-Halt Determinism (#317)
* test alt case

* fix determinism of gol-halt
2025-03-11 00:13:40 +01:00
joesharratt1229
e01910254d
added futoshiki and tower hanou (#316)
* added futoshiki and tower hanou

* corrected failed unit tests
2025-03-11 00:12:32 +01:00
joesharratt1229
30f5d823da
Curriculum/emoji mystery (#315)
* added emoji curriculum

* updated metadata

* added curriculum to register
2025-03-11 00:11:27 +01:00
joesharratt1229
0dce7adbad
Curriculum/cognition (#314)
* added rectangle count curriculum

* added number sequences

* registered curriculum
2025-03-11 00:10:28 +01:00
Andreas Koepf (aider)
d0b49cfffd feat: Add --category option to evaluate datasets from a specific category 2025-03-11 00:00:38 +01:00
Andreas Koepf
4109b5b72c update eval yaml config files 2025-03-10 00:48:32 +01:00
Andreas Koepf
a49463c323 use file stem name of palindrome_generation dataset 2025-03-10 00:39:29 +01:00
Andreas Koepf
1b004bf888 bump version 2025-03-10 00:32:57 +01:00
Zafir Stojanovski
e4b13bf51f
mini sudoku curriculum (#311) 2025-03-10 00:29:53 +01:00
Adefioye
f5141b32c5
Add complex arithmetic curriculum (#310)
* Add complex arithmetic curriculum
2025-03-10 00:28:51 +01:00
Zafir Stojanovski
a1dc28aa73
feat(env): String Synthesis Curriculum (#308)
* string synthesis curriculum

* difficulty metadata
2025-03-10 00:27:03 +01:00
Zafir Stojanovski
037905667e
string splitting curriculum (#307) 2025-03-10 00:25:56 +01:00
Zafir Stojanovski
83cd34e21b
letter counting curriculum (#312) 2025-03-10 00:24:42 +01:00
Zafir Stojanovski
b88cadf75a
feat(env): Word Sequence Reversal curriculum (#313)
* word sequence reversal curriculum

* metadata
2025-03-10 00:24:05 +01:00
Andreas Koepf (aider)
ec47c527a3 docs: Add ACRE dataset attribution to NOTICE.txt and source file 2025-03-10 00:21:57 +01:00
Adefioye
c8c3930797
Add ACRE(Abstract Causal REasoning Beyond Covariation) python generators (#199)
* Add acre python generators
* acre: improved prompt & formatting of examples, support arbitrary sizes

---------

Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
2025-03-10 00:09:54 +01:00
Rich Jones
e62b45d61c
BF Curricula and More (#309)
* bf curricula
* modulo grid curricula
* minor changes to how difficulty is stored

---------

Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
2025-03-09 18:22:22 +01:00
Zafir Stojanovski
54b216a5dc
string manipulation curriculum (#306) 2025-03-09 18:12:35 +01:00
Zafir Stojanovski
925283f342
string insertion curriculum (#305) 2025-03-09 18:11:29 +01:00
vncntt
af6120c095
add metadata for caesar cipher, graph coloring, decimal arithmetic (#304)
* add metadata for caesar cipher, graph coloring, decimal arithmetic

* delete comma

* clean up variables
2025-03-09 18:08:56 +01:00
vncntt
fc908d4cf4
Caesar cipher curriculum (#302)
* caesar cipher curriculum + tests
2025-03-09 08:23:32 +01:00
vncntt
e0f8ef061d
graph color curriculum (#303) 2025-03-09 08:20:47 +01:00
Zafir Stojanovski
2fca962847
ransom note curriculum (#300)
Co-authored-by: Andreas Köpf <andreas.koepf@xamla.com>
2025-03-08 21:00:13 +01:00
Zafir Stojanovski
bfa3a58829
palindrome partitioning curriculum (#299)
Co-authored-by: Andreas Köpf <andreas.koepf@xamla.com>
2025-03-08 20:58:59 +01:00
Zafir Stojanovski
194f08cad2
pool matrix curriculum (#298) 2025-03-08 20:57:22 +01:00
Zafir Stojanovski
5963cbd59e
rotten oranges curriculum (#297) 2025-03-08 20:56:46 +01:00
Zafir Stojanovski
6270e835bb
spiral matrix curriculum (#296) 2025-03-08 20:56:08 +01:00
Andreas Köpf
6615d8e662
Show curricula (#295)
* feat: Add debug_curricula.py script to generate CURRICULA.md with dataset curriculum details
2025-03-08 14:21:50 +01:00
Zafir Stojanovski
edab0389b6
rotate matrix curriculum (#294) 2025-03-08 01:58:54 +01:00
Zafir Stojanovski
8d4e9030c0
manipulate matrix curriculum (#293) 2025-03-08 01:57:37 +01:00
Zafir Stojanovski
e69ed78c26
feat(env): Isomorphic Strings Curriculum (#292)
* isomorphic strings curriculum

---------

Co-authored-by: Andreas Köpf <andreas.koepf@xamla.com>
2025-03-08 01:56:14 +01:00