Skip to content

Issues: open-thought/reasoning-gym

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

33 Open 40 Closed
33 Open 40 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Run r1 evals for logic datasets
#230 opened Feb 26, 2025 by joesharratt1229
Run r1 evals for graphs datasets
#229 opened Feb 26, 2025 by joesharratt1229
Run r1 evals for geometry datasets
#228 opened Feb 26, 2025 by joesharratt1229
Run r1 evals for games datasets
#227 opened Feb 26, 2025 by joesharratt1229
Run r1 evals for cognition datasets
#226 opened Feb 26, 2025 by joesharratt1229
Run r1 evals for code datasets
#225 opened Feb 26, 2025 by joesharratt1229
Run R1 evals for arc datasets
#224 opened Feb 26, 2025 by joesharratt1229
Run r1 evals for algebra datasets
#223 opened Feb 26, 2025 by joesharratt1229
Run r1 evals for arithmetic category dataset evaluations
#222 opened Feb 26, 2025 by joesharratt1229
Run r1 evals for algorithmic datasets evaluations
#221 opened Feb 26, 2025 by joesharratt1229
@joesharratt1229
fix counting_primes dataset metadata
#218 opened Feb 26, 2025 by vncntt
1
Fix tsumego score_answer function bug Something isn't working good first issue Good for newcomers
#211 opened Feb 25, 2025 by joesharratt1229
1
Run DeepSeekR1 evaluations evaluations
#210 opened Feb 25, 2025 by joesharratt1229
3
Port generator for BoxNet1 dataset
#209 opened Feb 25, 2025 by andreaskoepf
Port generator for Game 24 from CodeSteer dataset
#208 opened Feb 25, 2025 by andreaskoepf
Port dataset generator for Mahjong from CodeSteer dataset
#207 opened Feb 25, 2025 by andreaskoepf
@zafstojano
Run Llama 3 70b evaluations evaluations
#203 opened Feb 25, 2025 by joesharratt1229
@andreaskoepf
Run remaining o1 evaluations evaluations
#202 opened Feb 25, 2025 by joesharratt1229
Run o3-mini evaluations evaluations
#201 opened Feb 25, 2025 by joesharratt1229
@joesharratt1229
Add example of RL training using open-instruct
#189 opened Feb 22, 2025 by olliestanley
Add example of RL training with Axolotl
#162 opened Feb 19, 2025 by andreaskoepf
Add CODEI/O sampled subset dataset dataset
#160 opened Feb 18, 2025 by andreaskoepf
@olliestanley @zafstojano
3
Add Sonnet benchmark evals on arithmetic and algebra datasets
#107 opened Feb 11, 2025 by Adefioye
Interactive training with reasoning-gym server planning Ideation phase / overview, needs breakdown
#104 opened Feb 10, 2025 by andreaskoepf
@andreaskoepf
Check integration potential of SymBench dataset
#103 opened Feb 10, 2025 by andreaskoepf
2
ProTip! no:milestone will show everything without a milestone.