feat: Add support for Italian

app.py

@@ -176,6 +176,7 @@ FAROESE = Language(code="fo", name="Faroese")
 FRENCH = Language(code="fr", name="French")
 GERMAN = Language(code="de", name="German")
 ICELANDIC = Language(code="is", name="Icelandic")
+ITALIAN = Language(code="it", name="Italian")
 NORWEGIAN = Language(code="no", name="Norwegian")
 SWEDISH = Language(code="sv", name="Swedish")
 ALL_LANGUAGES = {
@@ -192,6 +193,7 @@ DATASETS = [
     Dataset(name="hotter-and-colder-sentiment", language=ICELANDIC, task=TEXT_CLASSIFICATION),
     Dataset(name="fosent", language=FAROESE, task=TEXT_CLASSIFICATION),
     Dataset(name="allocine", language=FRENCH, task=TEXT_CLASSIFICATION),
+    Dataset(name="sentipolc16", language=ITALIAN, task=TEXT_CLASSIFICATION),
 
     Dataset(name="suc3", language=SWEDISH, task=INFORMATION_EXTRACTION),
     Dataset(name="dansk", language=DANISH, task=INFORMATION_EXTRACTION),
@@ -203,6 +205,7 @@ DATASETS = [
     Dataset(name="conll-en", language=ENGLISH, task=INFORMATION_EXTRACTION),
     Dataset(name="fone", language=FAROESE, task=INFORMATION_EXTRACTION),
     Dataset(name="eltec", language=FRENCH, task=INFORMATION_EXTRACTION),
+    Dataset(name="multinerd-it", language=ITALIAN, task=INFORMATION_EXTRACTION),
 
     Dataset(name="scala-sv", language=SWEDISH, task=GRAMMAR),
     Dataset(name="scala-da", language=DANISH, task=GRAMMAR),
@@ -214,6 +217,7 @@ DATASETS = [
     Dataset(name="scala-en", language=ENGLISH, task=GRAMMAR),
     Dataset(name="scala-fo", language=FAROESE, task=GRAMMAR),
     Dataset(name="scala-fr", language=FRENCH, task=GRAMMAR),
+    Dataset(name="scala-it", language=ITALIAN, task=GRAMMAR),
 
     Dataset(name="scandiqa-da", language=DANISH, task=READING_COMPREHENSION),
     Dataset(name="norquad", language=NORWEGIAN, task=READING_COMPREHENSION),
@@ -224,6 +228,7 @@ DATASETS = [
     Dataset(name="squad-nl", language=DUTCH, task=READING_COMPREHENSION),
     Dataset(name="foqa", language=FAROESE, task=READING_COMPREHENSION),
     Dataset(name="fquad", language=FRENCH, task=READING_COMPREHENSION),
+    Dataset(name="squad-it", language=ITALIAN, task=READING_COMPREHENSION),
 
     Dataset(name="nordjylland-news", language=DANISH, task=SUMMARISATION),
     Dataset(name="mlsum", language=GERMAN, task=SUMMARISATION),
@@ -233,6 +238,7 @@ DATASETS = [
     Dataset(name="swedn", language=SWEDISH, task=SUMMARISATION),
     Dataset(name="cnn-dailymail", language=ENGLISH, task=SUMMARISATION),
     Dataset(name="orange-sum", language=FRENCH, task=SUMMARISATION),
+    Dataset(name="ilpost-sum", language=ITALIAN, task=SUMMARISATION),
 
     Dataset(name="danish-citizen-tests", language=DANISH, task=KNOWLEDGE),
     Dataset(name="danske-talemaader", language=DANISH, task=KNOWLEDGE),
@@ -243,6 +249,7 @@ DATASETS = [
     Dataset(name="mmlu-nl", language=DUTCH, task=KNOWLEDGE),
     Dataset(name="mmlu", language=ENGLISH, task=KNOWLEDGE),
     Dataset(name="mmlu-fr", language=FRENCH, task=KNOWLEDGE),
+    Dataset(name="mmlu-it", language=ITALIAN, task=KNOWLEDGE),
 
     Dataset(name="hellaswag-da", language=DANISH, task=COMMON_SENSE_REASONING),
     Dataset(name="hellaswag-no", language=NORWEGIAN, task=COMMON_SENSE_REASONING),
@@ -252,6 +259,7 @@ DATASETS = [
     Dataset(name="hellaswag-nl", language=DUTCH, task=COMMON_SENSE_REASONING),
     Dataset(name="hellaswag", language=ENGLISH, task=COMMON_SENSE_REASONING),
     Dataset(name="hellaswag-fr", language=FRENCH, task=COMMON_SENSE_REASONING),
+    Dataset(name="hellaswag-it", language=ITALIAN, task=COMMON_SENSE_REASONING),
 ]