|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- Samsung/samsum |
|
language: |
|
- en |
|
metrics: |
|
- bleu |
|
library_name: transformers |
|
pipeline_tag: summarization |
|
tags: |
|
- code |
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
The fine-tuned Google Pegasus model for text summarization utilizes a transformer-based encoder-decoder architecture optimized for abstractive summarization. Pre-trained using Gap-sentence Generation (GSG), the model learns to predict and generate missing sentences, enhancing its ability to understand context and importance within text. Fine-tuning involves training the pre-trained model on a specific summarization dataset to adapt it to the desired domain and style, improving its performance on task-specific summaries. |
|
|
|
|
|
- **Developed by:** [Akash Devbanshi] |
|
- **Model type:** [Text2Text Generation] |
|
- **License:** [Apache license 2.0] |
|
- **Finetuned from model [optional]:** [google/pegasus-cnn_dailymail] |
|
|
|
### Model Sources [optional] |
|
|
|
<!-- Provide the basic links for the model. --> |
|
|
|
- **Repository:** [google/pegasus-cnn_dailymail] |
|
|
|
|
|
## Uses |
|
|
|
The fine-tuned Google Pegasus model for text summarization can be used in various applications: |
|
|
|
Automated News Summarization: It can generate concise summaries of news articles, helping readers quickly grasp the main points. |
|
Summarizing Scientific Papers: Researchers can use it to produce brief overviews of lengthy academic papers, saving time. |
|
Content Creation: Bloggers and content creators can generate summaries for their articles or videos, making content more accessible. |
|
Customer Support: Summarize long customer service interactions or emails to provide quick insights for support agents. |
|
Legal Document Summarization: Lawyers and legal professionals can use it to summarize lengthy legal documents and contracts. |
