{"data":{"kind":"file","path":"README.md","version_id":"ph1fuvb7b0ibke6kq33bll16","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":1087,"modified_at":"2025-09-20T19:13:38.796000","content_hash":"ba4947c8a52b23182c767f92a0d4fe3d5fc2afb4316a3558677c0f45be4140a1"},"entries":[],"content":"# mbti\n\n### Overview\n- **Environment ID**: `mbti`\n- **Short description**: Single turn environment for guessing user's MBTI type based on tweets\n- **Tags**: \"single-turn\", \"train\", \"eval\", \"classification\", \"mbti\"\n\n### Datasets\n- **Primary dataset(s)**: kl08/myers-briggs-type-indicator\n- **Source links**: [hugginface](https://huggingface.co/datasets/kl08/myers-briggs-type-indicator/viewer/default/train?views%5B%5D=train)\n- **Split sizes**: 75% train 25% test\n\n### Task\n- **Type**: single-turn\n- **Parser**: XMLParser\n\n### Quickstart\nRun an evaluation with default settings:\n\n```bash\nuv run vf-eval mbti\n```\n\nConfigure model and sampling:\n\n```bash\nuv run vf-eval mbti -m gpt-4.1-mini -n 20 -r 3 -t 1024 -T 0.7 \n```\n\n### Metrics\nSummarize key metrics your rubric emits and how they’re interpreted.\n\n| Metric | Meaning |\n| ------ | ------- |\n| `format_reward` | Adherence to expected XML format |\n| `exact_answer_reward_func` | If the model correctly guessed the user's mbti type |\n| `partial_match_reward_func` | Gives rewards based on how many attributes where correctly guessed |\n\n","encoding":"utf-8","truncated":false,"total_bytes":1087},"status":null}