remove unecessary files , update tasks fux bug on tasks mapping in get_leaderboard df

refactor the code for better scalability and update tsac naming to sentiment analysis, adding madar dataset for transliteration and normalization eval

feat: enhance evaluation system and space management

remove dockerfile because it is not running both files ,

feat: enhance evaluation queue reliability and add stale job recovery

feat: enhance evaluation pipeline and error handling

Added traceback import to handle error traces

implement scripts for checking , add logging and update submission and integrate evaluation

implement evaluation and fix bugs

add evaluator integration

Refactor init_leaderboard function to raise ValueError for None DataFrame; improve error handling

Improve DataFrame handling in leaderboard functions; add debug print for empty DataFrame case

Refactor AutoEvalColumn usage for consistency and clarity; add debug prints for NaN checks in formatting functions

Duplicate from demo-leaderboard-backend/leaderboard