%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Bart Base Cnn R2 18.7 D23 Hybrid
This is a pruned and optimized BART-base model, specifically fine-tuned on the CNN/DailyMail dataset for summarization tasks.
Downloads 18
Release Time : 3/2/2022
Model Overview
This model is based on the facebook/bart-base architecture, optimized via the nn_pruning library, retaining 23% of linear layer weights and 45% of total weights, while removing 28.2% of attention heads, reducing model size while maintaining good performance.
Model Features
Efficient Pruning
Utilizes nn_pruning technology to retain only 23% of linear layer weights and 45% of original weights overall, significantly reducing model size.
Attention Head Optimization
Removed 28.2% of attention heads (61/216) via block pruning, improving inference efficiency.
Specialized Fine-tuning
Specifically optimized for the CNN/DailyMail news summarization dataset, achieving strong performance on Rouge metrics.
Model Capabilities
Text summarization generation
News content compression
English text processing
Use Cases
News Processing
News Summarization Generation
Automatically generates concise summaries of news articles
Rouge-1:41.43, Rouge-2:18.72, Rouge-L:38.35
Content Compression
Long Text Compression
Condenses lengthy articles into key information summaries
Featured Recommended AI Models