--- language: - en license: mit tags: - summarization - t5-large-summarization - pipeline:summarization thumbnail: https://huggingface.co/front/thumbnails/facebook.png model-index: - name: sysresearch101/t5-large-finetuned-xsum-cnn" results: - task: type: summarization name: Summarization dataset: name: xsum & cnn_dailymail type: xsum & cnn_dailymail config: 3.0.0 split: train metrics: - type: rouge value: name: ROUGE-1 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzI1MjFiNzJiYjVjNGMxNDM1MTU2YWU2MzIyMThhYjdkYmU5YTM4Yzk5OWYzYTcyZDQwNDg1NmIyYzNkZjFjMiIsInZlcnNpb24iOjF9.fVKnv7zkhNG6zLLpok10xyIHyYaGqiOShLXu9aDJvJNyZdKL82WHj_eP6Huv3hb5fmzlW8ZBJ_f7KOb98JjpDg - type: rouge value: name: ROUGE-2 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzMwOTllNmQ0MTMzNzI3MjMyMjVlZTU0YWI1OGYyNWY4ZWEyMGJmMzNjOWVjOTEyYmI2NGM3MjU2MmY1ZmU1YSIsInZlcnNpb24iOjF9.sUGKAQSY8k7JFCxCSjGC1Y8N6C-9zbeqALTr45erB30Q4yO7Poq9V2WoJQ3Eh6JJhHC8-V_REJtujCxmIJUPCQ - type: rouge value: name: ROUGE-L verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjYyNjk0NzdjMTViZmJkNGFlMDFhNWJjMjYyZDhjMzMzMjAyNmNiMzc0YTk5ZDI2ZTNlZDc1ZTE0ZTc1ODJkZCIsInZlcnNpb24iOjF9.m9PCgMGsGjD42_J2gokmzzHrh-sIHLf2txvmHzbNoV4vx_7JfF-LNoodgd_D6rPuJrebld5w6JwMgSI4abPQDg - type: rouge value: name: ROUGE-LSUM verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDMyODhjMjZlMjQzMDE0NDUyZjg3YjUyYmFmYmQzMjNkZGE5YjlhNzU4MDdhMmQwZjJjNjE2ZjZlMjQzNWJlYSIsInZlcnNpb24iOjF9.I_xeOcRbe_g3fLBeEraHI7JsxBz_rKlm893dylB0HGD4UyHuM5qtYyLu5p2ohhIoXX_W-PC-AFF-mlrUcBZhBw - type: loss value: name: loss verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWZiZGExY2M4NmM3ODhhZWVjYjk1MTg0M2YwMzc2Y2JkMmYxZjVkNzk0MDVhY2I2MzIyMDJiOWE4MmM3ZjIzYyIsInZlcnNpb24iOjF9.lFkphS1uVSwwr8h8dOq-AOghE8RYh9QRKL1f4QPzxxp8q-TiKEDwsWlyjnAaWXpUjNbMVMDETGiP5-pzKOomBg - type: gen_len value: name: gen_len verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmQwYmU0MjU5MTMxNGNiYWNmZGYwNDRmZGU2M2E0MTJmMTVjOThhZGM4NjU4MTI4ZDk5YzY4YjkyMDNlYzcxZSIsInZlcnNpb24iOjF9.6ZRzKoP9RGfr95lRPxJlETH-tbNZ-evNv8_AdkwULllUyIlpanmU0BF57EJHkIf4CYYuyjC_phaCfplAH8rmBQ - task: type: summarization name: Summarization dataset: name: xsum type: xsum config: default split: test metrics: - type: rouge value: 36.7656 name: ROUGE-1 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2QzMDg4NTM0ZTc5MjAzNTY4MmY1YTRiMWI3M2I2NDdjMTM4ZGNhYzZhOWQzMWI0MjJlYmU3MTg0ZjVjMTEyZSIsInZlcnNpb24iOjF9.AuKHql0LQs0zDQNn7zvySnX50GAC8jEWyYz-LtBgWj0dcad86J8yfHbIDswmgx2ur0S3yttw72qNExag_Fw7Dw - type: rouge value: 14.6898 name: ROUGE-2 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTE3ZTExY2M3MTIwMWY0ODRkZDI1YjU2ZjRkOGJjOGQyYjcxMTMxOWExN2Q0OGNkZmNiYzYzYzVhODY4YzEwOSIsInZlcnNpb24iOjF9.F1Q17sa8IAsW8ouQ2VDLq_VvHDxjuMjVU3rMfvkbmKxAjTDKVTiaG6Eg9uSKIYzgJoDSsxhsZcjH-J0gGQv3Dg - type: rouge value: 30.0646 name: ROUGE-L verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzI1NjE0NmI5Nzc3ODFiNDI5YzVhNjUzNzU1NzA0ZDMwMjFjZDE1YzUxNjZmZTAwZTM0MmVmN2ZkYWUwMjBiZSIsInZlcnNpb24iOjF9.xehN8zOV6050WvoLZIJ-l2zB93jWY_ugcydDDqV06XwdKwZ7l0TI8BoLDOO7Mw7dRmHOWLNruDJZnOnW3_3pCQ - type: rouge value: 30.0563 name: ROUGE-LSUM verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmU0OTVhYTY0ZDJmOTU3OWE5MzgxYzdhNmQ3MjM3YzM2MGIzOGViY2ZkMTI1ZWI4NDMwOTlkODBjOGE4NTE4ZCIsInZlcnNpb24iOjF9.FtNN06HKSgEB1tiWpToEVnNfzhQs9ZR59386YynOY6T6oKWxbIiRyItzYXobNw96lg5c2sE4vdJSfdtbBpkyDA - type: loss value: 1.6373405456542969 name: loss verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTVjYzI0MmMyY2IzYTE0NDUxY2FiMDM4Mjk2NTI1NTk0NjFiYTY2OWMxODRjNWJhYjU4ZWU5OTk4Y2E5N2RkOSIsInZlcnNpb24iOjF9.Cz5AQ-B8IAXmf1Xc_7UJ0pI9XKYHxDEwmoP3ZFsS2Wmbk1pUB8o_Y8AErBR8-Q60qR_ndw8eSwrI0EnPohYHCw - type: gen_len value: 18.6054 name: gen_len verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWRlMjM5MzAyMjEzYzdkODFmNDk4NDg5NWM4NWIxMTU4YWMxNzZjMGFjOWJiMDdkMjQyMTY0ZGFmYzA2OTA0YiIsInZlcnNpb24iOjF9.IFiGJEsyD7Uhj8bo9SsAgibk9qCXZH6IWaLKULLxBz5N8WXF2vc2Mfg5OThEzdrydPhJInRgp0jd8m-kF5nNCA - task: type: summarization name: Summarization dataset: name: cnn_dailymail type: cnn_dailymail config: 3.0.0 split: test metrics: - type: rouge value: 20.0169 name: ROUGE-1 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDljMWM0YjYxMDMyZTlhYmIzNmM2YzZkNmQwYjVjZTNmMGVhNzM2NTdjY2I3ODgzYWEwOTQ2NmY3ZjU2Zjk4MiIsInZlcnNpb24iOjF9.4cdcU0XAIgGdGFT4R6nd5qad1VoqY1dDXCq7jlcIeCfVcCwravKWuK8X8NggxevxC1BMeTd_jFJfuv3jWODSCw - type: rouge value: 5.0643 name: ROUGE-2 verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2QwNjlkNTVlZjk5MmIyZTIxYTExNjIzZjM4MjlkZDQ4NjViMjljZjg1NGI2ZmJiNGQ0NGVhMjRjNjg2MTA4OCIsInZlcnNpb24iOjF9._PcMo0Gfkjfs49sVX0yHnAgWrVptrAK6j2FiGRZaa3nUgHVyZRRstFOeK9fwZ26TtZ3FtIslfy6ia32IUfvACQ - type: rouge value: 14.4762 name: ROUGE-L verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWIyMGFmZmMxYjNhMTc4Y2Y3YTVjZDAwMWJhNzU2NjBkYWNlNGMwYzExMTEzZGQ3ZjFkYWIwMzE5NDgyOTNiNiIsInZlcnNpb24iOjF9.9LhQ7cYM5lpr9k9ngPjOZAsrGrc9MHFVfbd1HysL3blHds4SZv6ioOMameO7qVIlG2Ot1XslVbvN8l-_LSStDA - type: rouge value: 17.6812 name: ROUGE-LSUM verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGM4ZjJkMmUzNzZkNWZhZTc2YmUzZmJhN2U4YzQxM2VmNTk1ZDZkMjEyZDAwY2ZmNzVlMjFhZTY0M2UxZWFmMiIsInZlcnNpb24iOjF9.NSVmTw5_s5Zx_gQe2ibxo-R4O-KOi8yDZtQ2yExYxDFSMhs921eIi6KMBguNh6MAmCsEz-BFppI9gZ47XAP0Dg - type: loss value: 2.863785743713379 name: loss verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWRiZmFhOTY0MTE3NTE4MDcyZWUyMjM3MWI4NjIwY2I2YTI0YTQ1NzA3ODMzY2FiZDcwMjdjMWViNjk3NGEzNiIsInZlcnNpb24iOjF9.kygh8aIGin_1ucBoEMehNArgK0A1zwMK2Kd0JaAkFSnc3ZXvrYAdrSmxFfoGAlqYJT6bNL9UQievBlgyxt-aDg - type: gen_len value: 18.6581 name: gen_len verified: true verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTNkNTE4M2E4ZDI5NGZmN2I3YzM3ZTJkYmNjODdmMDk1ZjA4YzlmOGE1ODQxM2M4NjRiNTJjYzI0OTc2MmUxZCIsInZlcnNpb24iOjF9.6uPTg-C8HTQKq6Ppn0iwTWDz7P86_1cc5n6_3ct605etp4li79phSHS7TGpLKWeVSQKGpiSVOzUQhwslqyrVCg --- # T5-large Summarization Model Trained on the combined XSUM-CNN Daily Mail Dataset Finetuned T5 Large summarization model. ## LeaderBoard Rankings Currently ranks third (rouge-score) on the xsum dataset for summarization, trailing only Facebook's Bart-Large-Xsum and Google's Pegasus-Xsum. see : https://huggingface.co/spaces/autoevaluate/leaderboards?dataset=xsum , make sure to select Task : Summarization and Sorting Metric : Rouge Score ## Finetuning Corpus `t5-large-finetuned-xsum-cnn` model is based on `t5-large model` by [huggingface](https://huggingface.co/t5-large), finetuned using and fine-tuned on [CNN Daily Mail](https://huggingface.co/datasets/cnn_dailymail),and [XSUM](https://huggingface.co/datasets/xsum) datasets. ## Load Finetuned Model ```python from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, DataCollatorForSeq2Seq, Seq2SeqTrainingArguments, Seq2SeqTrainer tokenizer = AutoTokenizer.from_pretrained("sysresearch101/t5-large-finetuned-xsum-cnn") model = model = AutoModelForSeq2SeqLM.from_pretrained("sysresearch101/t5-large-finetuned-xsum-cnn") ARTICLE_TO_SUMMARIZE = "..." # generate summary input_ids = tokenizer.encode(ARTICLE_TO_SUMMARIZE, return_tensors='pt') summary_ids = model.generate(input_ids, min_length=20, max_length=80, num_beams=10, repetition_penalty=2.5, length_penalty=1.0, early_stopping=True, no_repeat_ngram_size=2, use_cache=True, do_sample = True, temperature = 0.8, top_k = 50, top_p = 0.95) summary_text = tokenizer.decode(summary_ids[0], skip_special_tokens=True) print(summary_text) Output: ``` ### How to use via a pipeline Here is how to use this model with the [pipeline API](https://huggingface.co/transformers/main_classes/pipelines.html): ```python from transformers import pipeline summarizer = pipeline("summarization", model="sysresearch101/t5-large-finetuned-xsum-cnn") 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. """ print(summarizer(ARTICLE, max_length=130, min_length=30, do_sample=False)) >>> [{'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.'}] ```