SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Generate: TF contrastive search with XLA support (#20050)

Browse Source 
* Add contrastive search
This commit is contained in:
Joao Gante
2022-11-07 10:54:29 +00:00
committed by GitHub
parent 504db92e7d
commit a0f8674303
5 changed files with 770 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

94
tests/models/bart/test_modeling_tf_bart.py
View File

@@ -550,6 +550,100 @@ class TFBartModelIntegrationTest(unittest.TestCase):
def tok(self):
return BartTokenizer.from_pretrained("facebook/bart-large")
@slow
def test_contrastive_search_bart(self):
article = (
" New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County, New York. A"
" year later, she got married again in Westchester County, but to a different man and without divorcing"
" her first husband. Only 18 days after that marriage, she got hitched yet again. Then, Barrientos"
' declared "I do" five more times, sometimes only within two weeks of each other. In 2010, she married'
" once more, this time in the Bronx. In an application for a marriage license, she stated it was her"
' "first and only" marriage. Barrientos, now 39, is facing two criminal counts of "offering a false'
' instrument for filing in the first degree," referring to her false statements on the 2010 marriage'
" license application, according to court documents. Prosecutors said the marriages were part of an"
" immigration scam. On Friday, she pleaded not guilty at State Supreme Court in the Bronx, according to"
" her attorney, Christopher Wright, who declined to comment further. After leaving court, Barrientos was"
" arrested and charged with theft of service and criminal trespass for allegedly sneaking into the New"
" York subway through an emergency exit, said Detective Annette Markowski, a police spokeswoman. In total,"
" Barrientos has been married 10 times, with nine of her marriages occurring between 1999 and 2002. All"
" occurred either in Westchester County, Long Island, New Jersey or the Bronx. She is believed to still be"
" married to four men, and at one time, she was married to eight men at once, prosecutors say. Prosecutors"
" said the immigration scam involved some of her husbands, who filed for permanent residence status"
" shortly after the marriages. Any divorces happened only after such filings were approved. It was"
" unclear whether any of the men will be prosecuted. The case was referred to the Bronx District"
" Attorney's Office by Immigration and Customs Enforcement and the Department of Homeland Security's"
' Investigation Division. Seven of the men are from so-called "red-flagged" countries, including Egypt,'
" Turkey, Georgia, Pakistan and Mali. Her eighth husband, Rashid Rajput, was deported in 2006 to his"
" native Pakistan after an investigation by the Joint Terrorism Task Force. If convicted, Barrientos faces"
" up to four years in prison. Her next court appearance is scheduled for May 18."
)
bart_tokenizer = BartTokenizer.from_pretrained("facebook/bart-large-cnn")
bart_model = TFBartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
input_ids = bart_tokenizer(
article, add_special_tokens=False, truncation=True, max_length=512, return_tensors="tf"
).input_ids
outputs = bart_model.generate(input_ids, penalty_alpha=0.5, top_k=5, max_length=64)
generated_text = bart_tokenizer.batch_decode(outputs, skip_special_tokens=True)
self.assertListEqual(
generated_text,
[
"Liana Barrientos, 39, pleaded not guilty to charges related to false marriage statements. "
"Prosecutors say she married at least 10 times, sometimes within two weeks of each other. She is "
"accused of being part of an immigration scam to get permanent residency. If convicted, she faces up "
"to four years in"
],
)
@slow
def test_contrastive_search_bart_xla(self):
article = (
" New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County, New York. A"
" year later, she got married again in Westchester County, but to a different man and without divorcing"
" her first husband. Only 18 days after that marriage, she got hitched yet again. Then, Barrientos"
' declared "I do" five more times, sometimes only within two weeks of each other. In 2010, she married'
" once more, this time in the Bronx. In an application for a marriage license, she stated it was her"
' "first and only" marriage. Barrientos, now 39, is facing two criminal counts of "offering a false'
' instrument for filing in the first degree," referring to her false statements on the 2010 marriage'
" license application, according to court documents. Prosecutors said the marriages were part of an"
" immigration scam. On Friday, she pleaded not guilty at State Supreme Court in the Bronx, according to"
" her attorney, Christopher Wright, who declined to comment further. After leaving court, Barrientos was"
" arrested and charged with theft of service and criminal trespass for allegedly sneaking into the New"
" York subway through an emergency exit, said Detective Annette Markowski, a police spokeswoman. In total,"
" Barrientos has been married 10 times, with nine of her marriages occurring between 1999 and 2002. All"
" occurred either in Westchester County, Long Island, New Jersey or the Bronx. She is believed to still be"
" married to four men, and at one time, she was married to eight men at once, prosecutors say. Prosecutors"
" said the immigration scam involved some of her husbands, who filed for permanent residence status"
" shortly after the marriages. Any divorces happened only after such filings were approved. It was"
" unclear whether any of the men will be prosecuted. The case was referred to the Bronx District"
" Attorney's Office by Immigration and Customs Enforcement and the Department of Homeland Security's"
' Investigation Division. Seven of the men are from so-called "red-flagged" countries, including Egypt,'
" Turkey, Georgia, Pakistan and Mali. Her eighth husband, Rashid Rajput, was deported in 2006 to his"
" native Pakistan after an investigation by the Joint Terrorism Task Force. If convicted, Barrientos faces"
" up to four years in prison. Her next court appearance is scheduled for May 18."
)
bart_tokenizer = BartTokenizer.from_pretrained("facebook/bart-large-cnn")
bart_model = TFBartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
input_ids = bart_tokenizer(
article, add_special_tokens=False, truncation=True, max_length=512, return_tensors="tf"
).input_ids
xla_generate = tf.function(bart_model.generate, jit_compile=True)
# no_repeat_ngram_size set to 0 because it isn't compatible with XLA, but doesn't change the original output
outputs = xla_generate(input_ids, penalty_alpha=0.5, top_k=5, max_length=64, no_repeat_ngram_size=0)
generated_text = bart_tokenizer.batch_decode(outputs, skip_special_tokens=True)
self.assertListEqual(
generated_text,
[
"Liana Barrientos, 39, pleaded not guilty to charges related to false marriage statements. "
"Prosecutors say she married at least 10 times, sometimes within two weeks of each other. She is "
"accused of being part of an immigration scam to get permanent residency. If convicted, she faces up "
"to four years in"
],
)
@slow
@require_tf