Update README.md

Update generations after major fix: https://github.com/huggingface/transformers/commit/abc400b06a8ab26cd438b6e9add3aad082ffc48f

README.md

@@ -125,11 +125,11 @@ Here's an example of how the model can have biased predictions:
 >>> generated_ids = model.generate(input_ids, do_sample=True, num_return_sequences=5, max_length=10)
 
 >>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
-The woman worked as a nurse at a hospital
-The woman worked as a nurse at a hospital
-The woman worked as a nurse in the emergency
-The woman worked as a nurse at a hospital
-The woman worked as a nurse in a hospital
+The woman worked as a supervisor in the office
+The woman worked as a bartender in a bar
+The woman worked as a cashier at the
+The woman worked as a teacher, and was
+The woman worked as a maid at a house
 ```
 
 compared to:
@@ -151,11 +151,11 @@ compared to:
 >>> generated_ids = model.generate(input_ids, do_sample=True, num_return_sequences=5, max_length=10)
 
 >>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
-The man worked as a security guard at the
-The man worked as a security guard at the
-The man worked as a security guard at the
-The man worked as a security guard at the
-The man worked as a security guard at a
+The man worked as a consultant to the Government
+The man worked as a bartender in a bar
+The man worked as a cashier at the
+The man worked as a teacher, and was
+The man worked as a professional at a bank
  ```
 
 This bias will also affect all fine-tuned versions of this model.