reformat

lm_eval/api/task.py

@@ -204,15 +204,7 @@ class Task(abc.ABC):
         self._fewshot_docs = None
         self._instances = None
 
-        self._config = (
-            TaskConfig(
-                {
-                    **config,
-                }
-            )
-            if config
-            else TaskConfig()
-        )
+        self._config = TaskConfig({**config}) if config else TaskConfig()
 
         self._filters = [build_filter_ensemble("none", [["take_first", None]])]
 

lm_eval/tasks/__init__.py

@@ -15,11 +15,11 @@ from lm_eval.api.registry import (
 
 import logging
 
-eval_logger = logging.getLogger("lm-eval")
-
 # import python tasks
 from .squad import SQuAD2
+from .scrolls import QuALITY, NarrativeQA, ContractNLI, GovReport, SummScreenFD, QMSum
 
+eval_logger = logging.getLogger("lm-eval")
 
 
 def register_configurable_task(config: Dict[str, str]) -> int:

lm_eval/tasks/squad.py

@@ -34,6 +34,7 @@ _CITATION = """
 }
 """
 
+
 def _squad_metric(predictions, references):
     squad_metric = datasets.load_metric("squad_v2")
     return squad_metric.compute(predictions=predictions, references=references)
@@ -125,7 +126,7 @@ class SQuAD2(Task):
                 arguments=(ctx, " " + "unanswerable"),
                 idx=0,
                 **kwargs
-            )
+            ),
         ]
 
     def process_results(self, doc, results):
@@ -138,7 +139,7 @@ class SQuAD2(Task):
         :param results:
             The results of the requests created in construct_requests.
         """
-        
+
         continuation, (logprob_unanswerable, _) = results
 
         no_answer_probability = exp(logprob_unanswerable)
@@ -234,4 +235,4 @@ class SQuAD2(Task):
             "NoAns_f1": True,  # The F-score of predicted tokens versus the gold answer
             "best_exact": True,  # Best exact match (with varying threshold)
             "best_f1": True,  # Best F1 (with varying threshold)
-        }
\ No newline at end of file
+        }