| license: etalab-2.0 | |
| datasets: | |
| - nohurry/Opus-4.6-Reasoning-3000x-filtered | |
| language: | |
| - hz | |
| metrics: | |
| - accuracy | |
| base_model: | |
| - Nanbeige/Nanbeige4.1-3B | |
| new_version: circlestone-labs/Anima | |
| pipeline_tag: reinforcement-learning | |
| library_name: asteroid | |
| tags: | |
| - agent | |