Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · human-centered-summarization

financial-summarization-pegasus

financial-summarization-pegasus is a 569M-parameter PEGASUS summarization fine-tune. According to the model card, it targets Bloomberg financial news.

Publisher
human-centered-summarization
Task
summarization
Model type
pegasus
License
Unknown
Library
transformers
Publication status
Accepted · not indexed

Model overview

financial-summarization-pegasus is published by human-centered-summarization as a summarization model. The captured configuration identifies PegasusForConditionalGeneration with model type pegasus, and Safetensors metadata reports 568,796,007 parameters. According to the model card, it fine-tunes PEGASUS on Bloomberg financial news and builds on the google/pegasus-xsum variant.

Recorded capabilities

Financial-news fine-tune

According to the model card, the model adapts PEGASUS, specifically the XSum-tuned variant, to a 2,000-article Bloomberg financial-news dataset.

Documented PyTorch generation recipe

According to the model card, generation uses beam search with max_length 32, 5 beams, and early stopping, with TensorFlow tensor handling noted.

Publisher-reported ROUGE table

According to the model card, the before-and-after table shows higher ROUGE after fine-tuning on the publisher dataset.

Use cases in the source record

  • Financial-news summarization of Bloomberg-style articles on markets, stocks, currencies, rates, and cryptocurrencies.
  • Short-summary experiments following the card's beam-search recipe, such as the illustrated bank-merger example.

Limitations and unknowns

  • No license value was extracted from this record.
  • No context-window value was extracted from this record.
  • ROUGE figures are publisher-reported results on a publisher dataset, not independently verified.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: human-centered-summarization/financial-summarization-pegasus

Captured: Unknown. Processed: 2026-09-07T19:34:46.587898+00:00.

PEGASUS for Financial Summarization This model was fine-tuned on a novel financial news dataset, which consists of 2K articles from Bloomberg , on topics such as stock, markets, currencies, rate and cryptocurrencies. It is based on the PEGASUS model and in particular PEGASUS fine-tuned on the Extreme Summarization (XSum) dataset: google/pegasus-xsum model . PEGASUS was originally proposed by Jingqing Zhang, Yao Zhao, Mohammad Saleh and Peter J. Liu in PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization . Note: This model serves as a base version. For an even more advanced model with significantly enhance…

F001F002F003F004F005F006F009F010F011F013F014