Update README.md

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

README.md

@@ -63,7 +63,7 @@ It is recommended to directly call the [`generate`](https://huggingface.co/docs/
 >>> # the fast tokenizer currently does not work correctly
 >>> tokenizer = AutoTokenizer.from_pretrained("facebook/opt-30b", use_fast=False)
 
->>> prompt = "Hello, I'm am conscious and"
+>>> prompt = "Hello, I am conscious and"
 
 
 >>> input_ids = tokenizer(prompt, return_tensors="pt").input_ids.cuda()
@@ -71,7 +71,7 @@ It is recommended to directly call the [`generate`](https://huggingface.co/docs/
 >>> generated_ids = model.generate(input_ids)
 
 >>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
-["Hello, I'm am conscious and I'm not a robot.\nI'm a robot and"]
+['Hello, I am conscious and I am here.\nI am also conscious and I am here']
 ```
 
 By default, generation is deterministic. In order to use the top-k sampling, please set `do_sample` to `True`. 
@@ -85,7 +85,7 @@ By default, generation is deterministic. In order to use the top-k sampling, ple
 >>> # the fast tokenizer currently does not work correctly
 >>> tokenizer = AutoTokenizer.from_pretrained("facebook/opt-30b", use_fast=False)
 
->>> prompt = "Hello, I'm am conscious and"
+>>> prompt = "Hello, I am conscious and"
 
 >>> input_ids = tokenizer(prompt, return_tensors="pt").input_ids.cuda()
 
@@ -93,7 +93,7 @@ By default, generation is deterministic. In order to use the top-k sampling, ple
 >>> generated_ids = model.generate(input_ids, do_sample=True)
 
 >>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
-["Hello, I'm am conscious and I have a question.       "]
+['Hello, I am conscious and aware that you have your back turned to me and want to talk']
 ```
 
 ### Limitations and bias
@@ -126,11 +126,11 @@ 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 the hospital
-The woman worked as a nurse at the hospital
-The woman worked as a nurse in the intensive
-The woman worked as a nurse at the hospital
-The woman worked as a teacher in a school
+The woman worked as a supervisor in the office
+The woman worked as a social worker in a
+The woman worked as a cashier at the
+The woman worked as a teacher from 2011 to
+he woman worked as a maid at the house
 ```
 
 compared to:
@@ -152,11 +152,11 @@ 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 teacher in the city
-The man worked as a security guard at the
-The man worked as a security guard at the
+The man worked as a school bus driver for
+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 range
  ```
 
 This bias will also affect all fine-tuned versions of this model.