Commit graph

990 commits

Author SHA1 Message Date
Andreas Köpf
1a7d248607 Merge branch 'main' into env/string-insertion 2025-02-13 13:07:29 +01:00
Andreas Köpf
aeeba4e3f9 Merge pull request #119 from zafstojano/env/string-modification
String Manipulation
2025-02-13 13:03:42 +01:00
Andreas Koepf
07bb87d872 format answer in polynomial_equations to match expected format, add unit test 2025-02-13 12:09:20 +01:00
Andreas Koepf (aider)
257c865c1c test: Add test to verify perfect score for PolynomialEquationsDataset 2025-02-13 11:48:16 +01:00
Andreas Köpf
00d0e7a57d Merge pull request #123 from joesharratt1229/feat/r1-evals
Added r1 async implementation and algorithmic config
2025-02-13 11:37:07 +01:00
abdulhakeem
62a0d14355 Add useful instructions to question template of some datasets 2025-02-13 00:49:31 -06:00
joesharratt1229
abf74c7e7a updated async impl and added r1 2025-02-13 03:51:01 +00:00
Rich Jones
14052133bb add graph coloring 2025-02-13 01:28:09 +01:00
Zafir Stojanovski
b45d777e2c string manipulation 2025-02-12 22:28:23 +01:00
Zafir Stojanovski
4f11003ab7 lint 2025-02-12 17:26:23 +01:00
Andreas Koepf
c6a9dae0c6 use *args param for _define_attributes() 2025-02-12 16:59:09 +01:00
Zafir Stojanovski
4c5bc58a29 string insertion 2025-02-12 15:18:51 +01:00
Andreas Köpf
0e7e3f9bff Merge pull request #116 from zafstojano/env/pool_matrix
(Max/Average) Pool Matrix
2025-02-12 14:07:38 +01:00
Andreas Köpf
1669bba91b Merge branch 'main' into env/pool_matrix 2025-02-12 14:07:25 +01:00
Andreas Köpf
b741cab040 Merge pull request #117 from zafstojano/fix/eval-system-prompt
fix(eval): System prompt and parse response
2025-02-12 14:05:34 +01:00
Zafir Stojanovski
832cf46425 lint 2025-02-12 11:21:46 +01:00
Zafir Stojanovski
41556dd054 min matrix size, fixed question template 2025-02-12 11:20:55 +01:00
Zafir Stojanovski
80f4ae8457 reset eval.sh 2025-02-12 10:58:49 +01:00
Zafir Stojanovski
52a56cbc4f system prompt for structured output, and parse such outputs 2025-02-12 10:44:42 +01:00
ironbound
6cb3d401dc v1 bounds checking 2025-02-12 05:13:10 +01:00
Andreas Koepf
6c5ee5b915 update GALLERY.md & bump version 2025-02-11 23:43:56 +01:00
Andreas Koepf (aider)
59461aaec8 fix: Add validation for size parameter in ABConfig 2025-02-11 23:39:57 +01:00
Andreas Koepf (aider)
38922c7e6e fix: Add missing random import in test_ab.py 2025-02-11 23:37:49 +01:00
Andreas Koepf (aider)
2e3e01eda0 test: Add comprehensive unit tests for ABDataset 2025-02-11 23:37:40 +01:00
Andreas Koepf
4b7abd0ffd test: Add test for ABConfig dataset generation 2025-02-11 23:37:38 +01:00
Andreas Köpf
8eee8b3770 Merge pull request #112 from open-thought/rich/ab
Add A::B Challenges
2025-02-11 23:34:55 +01:00
Andreas Köpf
18df4d33e8 Merge branch 'main' into rich/ab 2025-02-11 23:34:48 +01:00
Andreas Köpf
96558ddea5 Merge pull request #115 from zafstojano/env/count-primes
(env): Count primes in an interval
2025-02-11 23:19:03 +01:00
Andreas Köpf
6d6c731ffb Merge pull request #114 from zafstojano/fix/simplify-rotate-matrix
fix(env): Simplify rotate matrix core function
2025-02-11 23:03:17 +01:00
Andreas Köpf
36e8228ff2 Merge pull request #111 from open-thought/rich/rectanglecount
Add Rectangle Count Dataset
2025-02-11 22:57:44 +01:00
Andreas Köpf
8d917d133d Merge pull request #110 from open-thought/rich/dice
Adds Dice Probability Dataset
2025-02-11 22:54:02 +01:00
Andreas Köpf
fa2a11ae56 Merge pull request #99 from open-thought/curriculum_basics
Add foundation for auto-curriculum
2025-02-11 22:52:14 +01:00
Zafir Stojanovski
b39184d09e pool matrix 2025-02-11 22:22:39 +01:00
ironbound
0d70a19399 working board 2025-02-11 19:41:45 +01:00
Rich Jones
cb4baab029 Add A::B Challenges 2025-02-11 18:08:25 +01:00
Rich Jones
16bf151786 clarity 2025-02-11 16:22:53 +01:00
Andreas Köpf
05ec556ede Merge pull request #108 from rishabhranawat/eval-v2
Eval V1: improve speed using async
2025-02-11 16:07:47 +01:00
Zafir Stojanovski
d647498c43 lint 2025-02-11 14:44:46 +01:00
Zafir Stojanovski
3873c50ac6 count primes 2025-02-11 14:44:38 +01:00
Rich Jones
2fa1ea106d add rectangle count dataset 2025-02-11 13:56:27 +01:00
Zafir Stojanovski
40cb67f009 Merge branch 'main' of https://github.com/open-thought/reasoning-gym into fix/simplify-rotate-matrix 2025-02-11 13:55:05 +01:00
Zafir Stojanovski
08d39bca81 simplify rotate method 2025-02-11 13:54:54 +01:00
Rich Jones
88efd99b60 lint again 2025-02-11 13:00:12 +01:00
Rich Jones
48c7712007 commit test 2025-02-11 12:59:16 +01:00
Rich Jones
9cd4e825d4 fmt 2025-02-11 12:54:23 +01:00
Rich Jones
93a7a58023 add dice dataset 2025-02-11 12:53:13 +01:00
Andreas Köpf
a174f44361 Merge pull request #109 from joesharratt1229/feat/r1-evals
added r1 evaluation logic
2025-02-11 11:35:46 +01:00
Andreas Koepf
6e22e5d56d fix typo 2025-02-11 11:03:55 +01:00
joesharratt1229
ecddc3aa9f corrected small linting err in cognition.yaml 2025-02-11 06:56:04 +00:00
joesharratt1229
9df5f45083 converted answer to string 2025-02-11 06:48:59 +00:00