# High Rouge Score

A Russian news headline generation model based on the T5 architecture, optimized for short news texts, capable of generating summary-style headlines with 6-11 words

This model is a fine-tuned version of google/flan-t5-base on the samsum dialogue summarization dataset, specifically designed for dialogue summarization tasks.

A text summarization model fine-tuned on Vietnamese news datasets based on google/mt5-small, supporting automatic Vietnamese news summarization

A fine-tuned text summarization model based on barthez-orangesum-abstract, excelling in French text summarization tasks

A vision-language model fine-tuned on image folder datasets based on microsoft/git-base, primarily used for image caption generation tasks

An automatic summarization model trained based on FLAN-T5 large, suitable for English text summarization tasks.

This model is a fine-tuned version of facebook/bart-base on the XSum dataset, primarily used for summarization tasks.

A financial event summarization model fine-tuned based on BART-large architecture, with excellent performance on Rouge metrics

A news headline generation model fine-tuned from google/pegasus-multi_news, excelling at generating concise headlines from multi-document input

DistilBART is a distilled version of the BART model, focusing on text summarization tasks, significantly reducing model size and inference time while maintaining high performance.

DistilBART is a distilled version of the BART model, specifically optimized for text summarization tasks, significantly improving inference speed while maintaining high performance.

This is a pruned and optimized BART-base model specifically designed for summarization tasks, retaining 53% of the original model's weights.

A German abstract generation model fine-tuned on the mlsum de dataset based on facebook/bart-base

DistilBART is a distilled version of the BART model, focusing on text summarization tasks, significantly reducing model size and inference time while maintaining high performance.

This is a pruned and optimized BART-base model, specifically fine-tuned on the CNN/DailyMail dataset for summarization tasks.