fix: run lmms-eval --tasks list & lmms-eval --tasks list_with_num command correctly

[akawincent]

This PR restores the lmms-eval --tasks list and lmms-eval --tasks list_with_num command, fundamental features of lmms-eval that ensures users can query available tasks and their corresponding question counts.. Maintaining this feature provides better compatibility for future benchmark variants, such as vsi-bench-debias.

lmms-eval --tasks list

Before: Fail to display the task list correctly.

This script was launched with accelerate
2026-01-23 00:20:03.458 | INFO     | lmms_eval.__main__:cli_evaluate:308 - Verbosity set to INFO
2026-01-23 00:20:03.558 | INFO     | lmms_eval.__main__:cli_evaluate_single:392 - Evaluation tracker args: {}
2026-01-23 00:20:03.791 | INFO     | lmms_eval.__main__:cli_evaluate_single:428 - Available Tasks:
 - 

 - 

 - 

 - 

 - 

 - 

 - 

 - 

 - 

 - 

 - 

 - 

 - 

 - 

 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 -  
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - -
 - .
 - /
 - /
 - /
 - C
 - C
 - G
 - L
 - L
 - O
 - T
 - T
 - T
 - _
 - _
 - a
 - a
 - a
 - a
 - a
 - a
 - a
 - a
 - b
 - b
 - b
 - c
 - c
 - c
 - c
 - c
 - e
 - e
 - e
 - e
 - e
 - e
 - e
 - e
 - f
 - f
 - g
 - g
 - g
 - g
 - h
 - h
 - h
 - i
 - i
 - i
 - i
 - i
 - i
 - i
 - i
 - k
 - k
 - l
 - l
 - l
 - l
 - m
 - m
 - m
 - n
 - n
 - n
 - n
 - n
 - n
 - n
 - n
 - n
 - o
 - o
 - o
 - o
 - o
 - o
 - o
 - p
 - p
 - p
 - r
 - r
 - s
 - s
 - s
 - s
 - s
 - s
 - s
 - t
 - t
 - t
 - t
 - t
 - t
 - t
 - u
 - u
 - u
 - u
 - v
 - v
 - v
 - v
 - y
 - y
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |
 - |

After: Correctly output all registered tasks.

This script was launched with accelerate
2026-01-23 00:28:20.934 | INFO     | lmms_eval.__main__:cli_evaluate:308 - Verbosity set to INFO
2026-01-23 00:28:21.031 | INFO     | lmms_eval.__main__:cli_evaluate_single:392 - Evaluation tracker args: {}
2026-01-23 00:28:21.036 | INFO     | lmms_eval.__main__:cli_evaluate_single:428 - Available Tasks:
 - vsibench

lmms-eval --tasks list_with_num

Before: No results

This script was launched with accelerate
2026-01-23 01:14:11.348 | INFO     | lmms_eval.__main__:cli_evaluate:308 - Verbosity set to INFO
2026-01-23 01:14:11.445 | INFO     | lmms_eval.__main__:cli_evaluate_single:392 - Evaluation tracker args: {}
2026-01-23 01:14:11.448 | INFO     | lmms_eval.__main__:cli_evaluate_single:443 - 
======================================================================

        You are trying to check all the numbers in each task.
        This action will download the complete dataset.
        If the results are not clear initially, call this again.

======================================================================

After: Correctly output all registered tasks with their numbers.

This script was launched with accelerate
2026-01-23 01:12:03.028 | INFO     | lmms_eval.__main__:cli_evaluate:308 - Verbosity set to INFO
2026-01-23 01:12:03.130 | INFO     | lmms_eval.__main__:cli_evaluate_single:392 - Evaluation tracker args: {}
2026-01-23 01:12:03.135 | INFO     | lmms_eval.__main__:cli_evaluate_single:443 - 
======================================================================

        You are trying to check all the numbers in each task.
        This action will download the complete dataset.
        If the results are not clear initially, call this again.

======================================================================
Fetching 10 files: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:00<00:00, 7913.78it/s]
2026-01-23 01:12:06.618 | INFO     | lmms_eval.__main__:cli_evaluate_single:452 - 
Task : vsibench
 - #num : 5130