Spaces:
Sleeping
Sleeping
| from dataclasses import dataclass | |
| from enum import Enum | |
| class Task: | |
| benchmark: str | |
| metric: str | |
| col_name: str | |
| # Select your tasks here | |
| # --------------------------------------------------- | |
| class Tasks(Enum): | |
| # task_key, metric_key, name to display in the leaderboard | |
| task0 = Task("avg", "score", "Avg") | |
| task1 = Task("nar", "score", "Nar") | |
| task2 = Task("mt", "score", "MT") | |
| task3 = Task("con", "score", "Con") | |
| task4 = Task("if", "score", "IF") | |
| task5 = Task("scn", "score", "Scn") | |
| task6 = Task("saf", "score", "Saf") | |
| task7 = Task("att", "score", "Att") | |
| # --------------------------------------------------- | |
| # Your leaderboard name | |
| TITLE = """<h1 align="center" id="space-title">🎭 RoleRMBench Leaderboard</h1>""" | |
| # What does your leaderboard evaluate? | |
| INTRODUCTION_TEXT = """ | |
| RoleRMBench evaluates reward models on role-playing scenarios across multiple dimensions. | |
| """ | |
| CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results" | |
| CITATION_BUTTON_TEXT = r""" | |
| """ | |