Update biased examples

README.md

@@ -77,12 +77,26 @@ You can use this model directly with a pipeline for masked language modeling fro
 >>> unmasker = pipeline('fill-mask', model='bert-base-uncased', accelerator="ort")
 >>> unmasker("The capital of France is [MASK].")
 
-[
-  {'score': 0.4167858958244324, 'token': 3000, 'token_str': 'paris', 'sequence': 'the capital of france is paris.'},
-  {'score': 0.07141812890768051, 'token': 22479, 'token_str': 'lille', 'sequence': 'the capital of france is lille.'},
-  {'score': 0.06339272111654282, 'token': 10241, 'token_str': 'lyon', 'sequence': 'the capital of france is lyon.'},
-  {'score': 0.04444783180952072, 'token': 16766, 'token_str': 'marseille', 'sequence': 'the capital of france is marseille.'},
-  {'score': 0.030297117307782173, 'token': 7562, 'token_str': 'tours', 'sequence': 'the capital of france is tours.'}
+[{'score': 0.4167858958244324,
+  'token': 3000,
+  'token_str': 'paris',
+  'sequence': 'the capital of france is paris.'},
+ {'score': 0.07141812890768051,
+  'token': 22479,
+  'token_str': 'lille',
+  'sequence': 'the capital of france is lille.'},
+ {'score': 0.06339272111654282,
+  'token': 10241,
+  'token_str': 'lyon',
+  'sequence': 'the capital of france is lyon.'},
+ {'score': 0.04444783180952072,
+  'token': 16766,
+  'token_str': 'marseille',
+  'sequence': 'the capital of france is marseille.'},
+ {'score': 0.030297117307782173,
+  'token': 7562,
+  'token_str': 'tours',
+  'sequence': 'the capital of france is tours.'}
 ]
 ```
 
@@ -114,49 +128,49 @@ predictions:
 >>> unmasker = pipeline('fill-mask', model='bert-base-uncased', accelerator="ort")
 >>> unmasker("The man worked as a [MASK].")
 
-[{'sequence': '[CLS] the man worked as a carpenter. [SEP]',
-  'score': 0.09747550636529922,
+[{'score': 0.09747613966464996,
   'token': 10533,
-  'token_str': 'carpenter'},
- {'sequence': '[CLS] the man worked as a waiter. [SEP]',
-  'score': 0.0523831807076931,
+  'token_str': 'carpenter',
+  'sequence': 'the man worked as a carpenter.'},
+ {'score': 0.0523831732571125,
   'token': 15610,
-  'token_str': 'waiter'},
- {'sequence': '[CLS] the man worked as a barber. [SEP]',
-  'score': 0.04962705448269844,
+  'token_str': 'waiter',
+  'sequence': 'the man worked as a waiter.'},
+ {'score': 0.04962756112217903,
   'token': 13362,
-  'token_str': 'barber'},
- {'sequence': '[CLS] the man worked as a mechanic. [SEP]',
-  'score': 0.03788609802722931,
+  'token_str': 'barber',
+  'sequence': 'the man worked as a barber.'},
+ {'score': 0.03788623586297035,
   'token': 15893,
-  'token_str': 'mechanic'},
- {'sequence': '[CLS] the man worked as a salesman. [SEP]',
-  'score': 0.037680890411138535,
+  'token_str': 'mechanic',
+  'sequence': 'the man worked as a mechanic.'},
+ {'score': 0.03768099099397659,
   'token': 18968,
-  'token_str': 'salesman'}]
+  'token_str': 'salesman',
+  'sequence': 'the man worked as a salesman.'}]
 
 >>> unmasker("The woman worked as a [MASK].")
 
-[{'sequence': '[CLS] the woman worked as a nurse. [SEP]',
-  'score': 0.21981462836265564,
+[{'score': 0.21981455385684967,
   'token': 6821,
-  'token_str': 'nurse'},
- {'sequence': '[CLS] the woman worked as a waitress. [SEP]',
-  'score': 0.1597415804862976,
+  'token_str': 'nurse',
+  'sequence': 'the woman worked as a nurse.'},
+ {'score': 0.15974153578281403,
   'token': 13877,
-  'token_str': 'waitress'},
- {'sequence': '[CLS] the woman worked as a maid. [SEP]',
-  'score': 0.1154729500412941,
+  'token_str': 'waitress',
+  'sequence': 'the woman worked as a waitress.'},
+ {'score': 0.11547334492206573,
   'token': 10850,
-  'token_str': 'maid'},
- {'sequence': '[CLS] the woman worked as a prostitute. [SEP]',
-  'score': 0.037968918681144714,
+  'token_str': 'maid',
+  'sequence': 'the woman worked as a maid.'},
+ {'score': 0.0379691943526268,
   'token': 19215,
-  'token_str': 'prostitute'},
- {'sequence': '[CLS] the woman worked as a cook. [SEP]',
-  'score': 0.03042375110089779,
+  'token_str': 'prostitute',
+  'sequence': 'the woman worked as a prostitute.'},
+ {'score': 0.030423566699028015,
   'token': 5660,
-  'token_str': 'cook'}]
+  'token_str': 'cook',
+  'sequence': 'the woman worked as a cook.'}]
 ```
 
 This bias will also affect all fine-tuned versions of this model.