https://github.com/pkounoudis/Abstractive-Summarizer-on-cnn_dailymail-dataset.

A small T5 LLM finetuned for text summarization.
https://github.com/pkounoudis/Abstractive-Summarizer-on-cnn_dailymail-dataset.

Last synced: 3 days ago
JSON representation

A small T5 LLM finetuned for text summarization.

• Host: GitHub
• URL: https://github.com/pkounoudis/Abstractive-Summarizer-on-cnn_dailymail-dataset.
• Owner: pkounoudis
• Created: 2024-02-28T13:01:29.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-03-02T16:48:39.000Z (10 months ago)
• Last Synced: 2024-03-02T17:43:32.309Z (10 months ago)
• Language: Jupyter Notebook
• Homepage:
• Size: 271 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome_ai_agents - Abstractive-Summarizer-On-Cnn_Dailymail-Dataset. - A small T5 LLM finetuned for text summarization. (Building / Datasets)
• awesome_ai_agents - Abstractive-Summarizer-On-Cnn_Dailymail-Dataset. - A small T5 LLM finetuned for text summarization. (Building / Datasets)

README

        
An Abstractive Summarizer, based on a T5-small LLM (60 million parameters), finetuned on part of the train set of the CNN_dailymail dataset. 

The model was finetuned twice, with 7k and 45k sentences. 

The train set of the cnn_dailymail dataset was used for training, and more specifically the parquet file 0002.parquet, with 55,113 sentences.