Downloads · 30 days
9
16% of all-time downloads
pegasus-large-cnn-quantized
aloutzidis/pegasus-large-cnn-quantized
pegasus-large-cnn-quantized is a machine learning model from aloutzidis. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
57
Public
Repo size
4.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin2.3 GB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- pegasus
- Access
- Public
- Created
- May 11, 2023
- Updated
- May 12, 2023
- SHA
- 013d5f90
Datasets
Spaces
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
pegasus-large-cnn-quantized
This model is a fine-tuned version of google/pegasus-large on CNN/DailyMail dataset.
Model description
Online news reading has become one of the most popular ways to consume the latest news. News aggregation websites such as Google News and Yahoo News have made it easy for users to find the latest news and provide thousands of news stories from hundreds of news publishers. As people have limited time, reading all news articles is not feasible. The success of zero-shot and few-shot prompting with models like GPT-3 has led to a paradigm shift in NLP. So, in the era of ChatGPT, we we conducted experiments using various large language models (LLMs) such as BART and PEGASUS to improve the quality and coherence of the generated news summaries.
This is a quantized model finetuned on the CNN/DailyMail dataset.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 123
- optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Framework versions
- Transformers 4.29.0
- Pytorch 1.13.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
- Library
- transformers
- Type
- pegasus
- License
- apache-2.0
- Languages
- en
- Created
- May 11, 2023
- Updated
- May 12, 2023