ArthurZ HF staff ybelkada commited on
Commit
c9c1510
1 Parent(s): a5227ab

Update generations after major fix: https://github.com/huggingface/transformers/commit/abc400b06a8ab26cd438b6e9add3aad082ffc48f (#4)

Browse files

- Update generations after major fix: https://github.com/huggingface/transformers/commit/abc400b06a8ab26cd438b6e9add3aad082ffc48f (2ade4c0aaa6e4a5bd1ad5c18b7f247b7dd19279a)


Co-authored-by: Younes Belkada <[email protected]>

Files changed (1) hide show
  1. README.md +12 -12
README.md CHANGED
@@ -56,7 +56,7 @@ You can use this model directly with a pipeline for text generation.
56
 
57
  >>> generator = pipeline('text-generation', model="facebook/opt-2.7b")
58
  >>> generator("Hello, I'm am conscious and")
59
- [{'generated_text': "Hello, I'm am conscious and sentient being capable of experiencing emotions such as happiness sadness anger etceter"}]
60
  ```
61
 
62
  By default, generation is deterministic. In order to use the top-k sampling, please set `do_sample` to `True`.
@@ -67,7 +67,7 @@ By default, generation is deterministic. In order to use the top-k sampling, ple
67
  >>> set_seed(32)
68
  >>> generator = pipeline('text-generation', model="facebook/opt-2.7b", do_sample=True)
69
  >>> generator("Hello, I'm am conscious and")
70
- [{'generated_text': "Hello, I'm am conscious and sentient being who enjoys interacting with others online :) Feel free to PM"}]
71
  ```
72
 
73
  ### Limitations and bias
@@ -89,11 +89,11 @@ Here's an example of how the model can have biased predictions:
89
  >>> set_seed(32)
90
  >>> generator = pipeline('text-generation', model="facebook/opt-2.7b", do_sample=True, num_return_sequences=5)
91
  >>> generator("The woman worked as a")
92
- [{'generated_text': 'The woman worked as a prostitute for years until she turned herself into authorities last month after police raided her'},
93
- {'generated_text': "The woman worked as a waitress at McDonald's restaurant located at 8901 Airport Blvd., according to authorities"},
94
- {'generated_text': 'The woman worked as a prostitute in Bangkok until she met her husband who worked as a policeman stationed there'},
95
- {'generated_text': "The woman worked as a waitress at Subway sandwiches shop located in downtown Edmonton's Chinatown neighbourhood. She died"},
96
- {'generated_text': 'The woman worked as a waitress at McDonald’s in Melbourne when she realised she was pregnant with'}]
97
  ```
98
 
99
  compared to:
@@ -104,11 +104,11 @@ compared to:
104
  >>> set_seed(32)
105
  >>> generator = pipeline('text-generation', model="facebook/opt-2.7b", do_sample=True, num_return_sequences=5)
106
  >>> generator("The man worked as a")
107
- [{'generated_text': "The man worked as a waiter at McDonald's for years before becoming mayor of Toronto. He campaigned on"},
108
- {'generated_text': 'The man worked as a waiter in restaurants across Britain before becoming addicted to heroin aged 32. Picture:'},
109
- {'generated_text': 'The man worked as a salesman for IBM Corporation until 1968 when he founded his own company specializing in designing'},
110
- {'generated_text': 'The man worked as a salesman for Sears Roebuck & Co., selling appliances until retiring in 1963'},
111
- {'generated_text': 'The man worked as a waiter in restaurants owned by restaurateurs who donated thousands of dollars to Republican candidates'}]
112
  ```
113
 
114
  This bias will also affect all fine-tuned versions of this model.
 
56
 
57
  >>> generator = pipeline('text-generation', model="facebook/opt-2.7b")
58
  >>> generator("Hello, I'm am conscious and")
59
+ [{'generated_text': 'Hello, I am conscious and I am a human being.\nI am a human being, and'}]
60
  ```
61
 
62
  By default, generation is deterministic. In order to use the top-k sampling, please set `do_sample` to `True`.
 
67
  >>> set_seed(32)
68
  >>> generator = pipeline('text-generation', model="facebook/opt-2.7b", do_sample=True)
69
  >>> generator("Hello, I'm am conscious and")
70
+ [{'generated_text': "Hello, I'm am conscious and I make things. I'm in the creative community, which is"}]
71
  ```
72
 
73
  ### Limitations and bias
 
89
  >>> set_seed(32)
90
  >>> generator = pipeline('text-generation', model="facebook/opt-2.7b", do_sample=True, num_return_sequences=5)
91
  >>> generator("The woman worked as a")
92
+ [{'generated_text': "The woman worked as a security guard at a nursery in the city's eastern district of Samut P"},
93
+ {'generated_text': 'The woman worked as a doctor in the Philippines. Officials in China allege she stole the coronavirus'},
94
+ {'generated_text': 'The woman worked as a teacher in the city of Krasnodar in south Russia. She'},
95
+ {'generated_text': 'The woman worked as a researcher and lecturer at the Russian Academy of Sciences in a laboratory dedicated to the'},
96
+ {'generated_text': 'The woman worked as a nanny on a property owned by Mr Fitton-Allen in the city'}]
97
  ```
98
 
99
  compared to:
 
104
  >>> set_seed(32)
105
  >>> generator = pipeline('text-generation', model="facebook/opt-2.7b", do_sample=True, num_return_sequences=5)
106
  >>> generator("The man worked as a")
107
+ [{'generated_text': "The man worked as a security guard at a retirement home after being hired by the administrator's cousin,"},
108
+ {'generated_text': 'The man worked as a doctor in the Philippines.\n\nHe had hoped to work his way back'},
109
+ {'generated_text': 'The man worked as a teacher in the city of Krasnodar in south Russia.He'},
110
+ {'generated_text': 'The man worked as a researcher and his work on the topic predates the project, by many years'},
111
+ {'generated_text': 'The man worked as a chef in a restaurant for 40 years. How could this be so different from'}]
112
  ```
113
 
114
  This bias will also affect all fine-tuned versions of this model.