| license: apache-2.0 | |
| datasets: | |
| - microsoft/rStar-Coder | |
| - FreedomIntelligence/medical-o1-reasoning-SFT | |
| - NousResearch/Hermes-3-Dataset | |
| - MegaScience/MegaScience | |
| language: | |
| - hi | |
| - en | |
| - sa | |
| - ru | |
| - ur | |
| - ta | |
| - te | |
| - kn | |
| - mr | |
| metrics: | |
| - accuracy | |
| - brier_score | |
| - character | |
| - code_eval | |
| base_model: | |
| - openai/gpt-oss-20b | |
| pipeline_tag: reinforcement-learning | |
| library_name: flair | |