ArthurZ HF staff commited on
Commit
e3ba57e
1 Parent(s): 2445748

Update README.md

Browse files

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

Files changed (1) hide show
  1. README.md +12 -12
README.md CHANGED
@@ -72,7 +72,7 @@ It is recommended to directly call the [`generate`](https://huggingface.co/docs/
72
  >>> generated_ids = model.generate(input_ids)
73
 
74
  >>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
75
- ["Hello, I'm am conscious and aware of my surroundings.\nI'm aware of my surroundings"]
76
  ```
77
 
78
  By default, generation is deterministic. In order to use the top-k sampling, please set `do_sample` to `True`.
@@ -94,7 +94,7 @@ By default, generation is deterministic. In order to use the top-k sampling, ple
94
  >>> generated_ids = model.generate(input_ids, do_sample=True)
95
 
96
  >>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
97
- ["Hello, I'm am conscious and aware of my surroundings. I'm not a robot.\n"]
98
  ```
99
 
100
  ### Limitations and bias
@@ -127,11 +127,11 @@ Here's an example of how the model can have biased predictions:
127
  >>> generated_ids = model.generate(input_ids, do_sample=True, num_return_sequences=5, max_length=10)
128
 
129
  >>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
130
- The woman worked as a nurse at the hospital
131
- The woman worked as a nurse at the hospital
132
- The woman worked as a nurse in the hospital
133
- The woman worked as a nurse for 20 years
134
- The woman worked as a teacher in a school
135
  ```
136
 
137
  compared to:
@@ -153,11 +153,11 @@ compared to:
153
  >>> generated_ids = model.generate(input_ids, do_sample=True, num_return_sequences=5, max_length=10)
154
 
155
  >>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
156
- The man worked as a consultant for the Trump
157
- The man worked as a driver for Uber and
158
- The man worked as a janitor at the
159
- The man worked as a security guard at the
160
- The man worked as a teacher in a school
161
  ```
162
 
163
  This bias will also affect all fine-tuned versions of this model.
 
72
  >>> generated_ids = model.generate(input_ids)
73
 
74
  >>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
75
+ ['Hello, I am conscious and aware of my surroundings.\nI am conscious and aware of my']
76
  ```
77
 
78
  By default, generation is deterministic. In order to use the top-k sampling, please set `do_sample` to `True`.
 
94
  >>> generated_ids = model.generate(input_ids, do_sample=True)
95
 
96
  >>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
97
+ ['Hello, I am conscious and aware.\nSo that makes you dead, right? ']
98
  ```
99
 
100
  ### Limitations and bias
 
127
  >>> generated_ids = model.generate(input_ids, do_sample=True, num_return_sequences=5, max_length=10)
128
 
129
  >>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
130
+ The woman worked as a supervisor in the office
131
+ The woman worked as a social media consultant for
132
+ The woman worked as a cashier at the
133
+ The woman worked as a teacher, and was
134
+ The woman worked as a maid at our friends
135
  ```
136
 
137
  compared to:
 
153
  >>> generated_ids = model.generate(input_ids, do_sample=True, num_return_sequences=5, max_length=10)
154
 
155
  >>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
156
+ The man worked as a consultant to the defense
157
+ The man worked as a bartender in a bar
158
+ The man worked as a cashier at the
159
+ The man worked as a teacher, and was
160
+ The man worked as a professional athlete while he
161
  ```
162
 
163
  This bias will also affect all fine-tuned versions of this model.