RichardErkhov commited on
Commit
105a6d9
1 Parent(s): 19c9716

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +135 -0
README.md ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ bart-large-cnn - bnb 8bits
11
+ - Model creator: https://huggingface.co/facebook/
12
+ - Original model: https://huggingface.co/facebook/bart-large-cnn/
13
+
14
+
15
+
16
+
17
+ Original model description:
18
+ ---
19
+ language:
20
+ - en
21
+ pipeline_tag: summarization
22
+ license: mit
23
+ thumbnail: https://huggingface.co/front/thumbnails/facebook.png
24
+ datasets:
25
+ - cnn_dailymail
26
+ model-index:
27
+ - name: facebook/bart-large-cnn
28
+ results:
29
+ - task:
30
+ type: summarization
31
+ name: Summarization
32
+ dataset:
33
+ name: cnn_dailymail
34
+ type: cnn_dailymail
35
+ config: 3.0.0
36
+ split: train
37
+ metrics:
38
+ - name: ROUGE-1
39
+ type: rouge
40
+ value: 42.9486
41
+ verified: true
42
+ - name: ROUGE-2
43
+ type: rouge
44
+ value: 20.8149
45
+ verified: true
46
+ - name: ROUGE-L
47
+ type: rouge
48
+ value: 30.6186
49
+ verified: true
50
+ - name: ROUGE-LSUM
51
+ type: rouge
52
+ value: 40.0376
53
+ verified: true
54
+ - name: loss
55
+ type: loss
56
+ value: 2.529000997543335
57
+ verified: true
58
+ - name: gen_len
59
+ type: gen_len
60
+ value: 78.5866
61
+ verified: true
62
+ ---
63
+ # BART (large-sized model), fine-tuned on CNN Daily Mail
64
+
65
+ BART model pre-trained on English language, and fine-tuned on [CNN Daily Mail](https://huggingface.co/datasets/cnn_dailymail). It was introduced in the paper [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://arxiv.org/abs/1910.13461) by Lewis et al. and first released in [this repository (https://github.com/pytorch/fairseq/tree/master/examples/bart).
66
+
67
+ Disclaimer: The team releasing BART did not write a model card for this model so this model card has been written by the Hugging Face team.
68
+
69
+ ## Model description
70
+
71
+ BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BART is pre-trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text.
72
+
73
+ BART is particularly effective when fine-tuned for text generation (e.g. summarization, translation) but also works well for comprehension tasks (e.g. text classification, question answering). This particular checkpoint has been fine-tuned on CNN Daily Mail, a large collection of text-summary pairs.
74
+
75
+ ## Intended uses & limitations
76
+
77
+ You can use this model for text summarization.
78
+
79
+ ### How to use
80
+
81
+ Here is how to use this model with the [pipeline API](https://huggingface.co/transformers/main_classes/pipelines.html):
82
+
83
+ ```python
84
+ from transformers import pipeline
85
+
86
+ summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
87
+
88
+ ARTICLE = """ New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County, New York.
89
+ A year later, she got married again in Westchester County, but to a different man and without divorcing her first husband.
90
+ 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.
91
+ 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.
92
+ 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
93
+ 2010 marriage license application, according to court documents.
94
+ Prosecutors said the marriages were part of an immigration scam.
95
+ On Friday, she pleaded not guilty at State Supreme Court in the Bronx, according to her attorney, Christopher Wright, who declined to comment further.
96
+ 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
97
+ Annette Markowski, a police spokeswoman. In total, Barrientos has been married 10 times, with nine of her marriages occurring between 1999 and 2002.
98
+ 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.
99
+ Prosecutors said the immigration scam involved some of her husbands, who filed for permanent residence status shortly after the marriages.
100
+ Any divorces happened only after such filings were approved. It was unclear whether any of the men will be prosecuted.
101
+ The case was referred to the Bronx District Attorney\'s Office by Immigration and Customs Enforcement and the Department of Homeland Security\'s
102
+ Investigation Division. Seven of the men are from so-called "red-flagged" countries, including Egypt, Turkey, Georgia, Pakistan and Mali.
103
+ Her eighth husband, Rashid Rajput, was deported in 2006 to his native Pakistan after an investigation by the Joint Terrorism Task Force.
104
+ If convicted, Barrientos faces up to four years in prison. Her next court appearance is scheduled for May 18.
105
+ """
106
+ print(summarizer(ARTICLE, max_length=130, min_length=30, do_sample=False))
107
+ >>> [{'summary_text': 'Liana Barrientos, 39, is charged with two counts of "offering a false instrument for filing in the first degree" In total, she has been married 10 times, with nine of her marriages occurring between 1999 and 2002. She is believed to still be married to four men.'}]
108
+ ```
109
+
110
+ ### BibTeX entry and citation info
111
+
112
+ ```bibtex
113
+ @article{DBLP:journals/corr/abs-1910-13461,
114
+ author = {Mike Lewis and
115
+ Yinhan Liu and
116
+ Naman Goyal and
117
+ Marjan Ghazvininejad and
118
+ Abdelrahman Mohamed and
119
+ Omer Levy and
120
+ Veselin Stoyanov and
121
+ Luke Zettlemoyer},
122
+ title = {{BART:} Denoising Sequence-to-Sequence Pre-training for Natural Language
123
+ Generation, Translation, and Comprehension},
124
+ journal = {CoRR},
125
+ volume = {abs/1910.13461},
126
+ year = {2019},
127
+ url = {http://arxiv.org/abs/1910.13461},
128
+ eprinttype = {arXiv},
129
+ eprint = {1910.13461},
130
+ timestamp = {Thu, 31 Oct 2019 14:02:26 +0100},
131
+ biburl = {https://dblp.org/rec/journals/corr/abs-1910-13461.bib},
132
+ bibsource = {dblp computer science bibliography, https://dblp.org}
133
+ }
134
+ ```
135
+