added new filter to remove whitespace in the front of a prediction

lm_eval/filters/__init__.py

@@ -8,6 +8,7 @@ FILTER_REGISTRY = {
     "regex": extraction.RegexFilter,
     "majority_vote": selection.MajorityVoteFilter,
     "take_first_k": selection.TakeKFilter,
+    "remove_whitespace": extraction.WhitespaceFilter,
     # TODO: implement this filter. either it should take in an arbitrary "scoring"/reward function
     # that takes an input and returns a scalar and then should select the max reward,
     # or should implement different filters for different ways of handling a reward model's inference.

lm_eval/filters/extraction.py

@@ -36,3 +36,27 @@ class RegexFilter(Filter):
         # print(filtered_resps)
 
         return filtered_resps
+
+
+class WhitespaceFilter(Filter):
+    """ """
+
+    def __init__(self):
+        pass
+
+    def apply(self, resps):
+
+        def filter_set(inst):
+
+            filtered_resp = []
+            for resp in inst:
+                if resp.startswith(" "):
+                    resp = resp[1:]
+
+                filtered_resp.append(resp)
+
+            return filtered_resp
+
+        filtered_resps = [filter_set(resp) for resp in resps]
+
+        return filtered_resps
\ No newline at end of file