fix tasks list (#906)

* Update registry.py

refix the tasks list command

* Update registry.py

feat(tasks): add suite filtering and fix community task discovery

- Revert the community task path fix
- Add --suites parameter to lighteval tasks list
- Default to core suites only to prevent overwhelming output
- Add dependency checking for multilingual tasks

* Update main_tasks.py

feat(tasks): add suite filtering and fix community task discovery

- Revert the community task path fix
- Add --suites parameter to lighteval tasks list
- Default to core suites only to prevent overwhelming output
- Add dependency checking for multilingual tasks

* Update aimo_evals.py

fix `community` tasks loading error due to an unexpected keyword argument 'metric'

* Update german_rag_evals.py

fix `community` tasks loading error due to an unexpected keyword argument 'metric'

* Update oz_evals.py

fix `community` tasks loading error due to an unexpected keyword argument 'metric'

* Update serbian_eval.py

fix `community` tasks loading error due to an unexpected keyword argument 'metric'

* Update turkic_evals.py

fix `community` tasks loading error due to an unexpected keyword argument 'metric'

* Update turkic_evals.py

Remove the import of `MetricUseCase` because it is given the following error:
`Failed to load community tasks from turkic_evals: cannot import name 'MetricUseCase' from 'lighteval.metrics.utils.metric_utils' (/~/repos/lighteval-070825/lighteval/src/lighteval/metrics/utils/metric_utils.py) (registry.py:70)`

* Update registry.py

adding 'all' as one option in the `--suites` arg to simplify getting the list of both core and optional suites

* Update main_tasks.py

adding 'all' as one option in the `--suites` arg to simplify getting the list of both core and optional suites

Author: alielfilali01

community_tasks/aimo_evals.py

@@ -49,7 +49,7 @@ def aimo_prompt(line, task_name: str = None):
     evaluation_splits=["train"],
     few_shots_split="train",
     few_shots_select="sequential",
-    metric=[Metrics.quasi_exact_match_math],
+    metrics=[Metrics.quasi_exact_match_math],
     generation_size=2048,
     stop_sequence=None,
 )

community_tasks/german_rag_evals.py

@@ -162,7 +162,7 @@ def prompt_fn_context_question_match(line, task_name: str = None):
     evaluation_splits=["test"],
     few_shots_split="test",
     few_shots_select="sequential",
-    metric=[Metrics.loglikelihood_acc],
+    metrics=[Metrics.loglikelihood_acc],
     version=1,
 )
 
@@ -179,7 +179,7 @@ def prompt_fn_context_question_match(line, task_name: str = None):
     evaluation_splits=["test"],
     few_shots_split="test",
     few_shots_select="sequential",
-    metric=[Metrics.loglikelihood_acc],
+    metrics=[Metrics.loglikelihood_acc],
     version=1,
 )
 
@@ -197,7 +197,7 @@ def prompt_fn_context_question_match(line, task_name: str = None):
     evaluation_splits=["test"],
     few_shots_split="test",
     few_shots_select="sequential",
-    metric=[Metrics.loglikelihood_acc],
+    metrics=[Metrics.loglikelihood_acc],
     version=1,
 )
 
@@ -214,7 +214,7 @@ def prompt_fn_context_question_match(line, task_name: str = None):
     evaluation_splits=["test"],
     few_shots_split="test",
     few_shots_select="sequential",
-    metric=[Metrics.loglikelihood_acc],
+    metrics=[Metrics.loglikelihood_acc],
     version=1,
 )
 

community_tasks/oz_evals.py

@@ -78,7 +78,7 @@ def prompt_fn_oz_eval_task(line, task_name: str = None):
     evaluation_splits=["test"],
     few_shots_split=None,
     few_shots_select=None,
-    metric=[Metrics.loglikelihood_acc],
+    metrics=[Metrics.loglikelihood_acc],
     version=0,
 )