philschmid / summarization Open weights updated 3 years ago

bart-large-cnn-samsum

Name: bart-large-cnn-samsum
Author: philschmid

> If you want to use the model you should try a newer fine-tuned FLAN-T5 version philschmid/flan-t5-base-samsum out socring the BART version with +6 on ROGUE1 achieving 47.24.

Params

—

Context

1,024

Downloads 30d

73 K

Likes

268

Commercial use: allowed mit Not gated 1 languages View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 7 K in the last 30 days (9.0%)

130 K67 K

Jul 28Sep 1Oct 6Nov 10

Specifications

Architecture: BartForConditionalGeneration
Context length: 1,024
Vocabulary: 50,264
Licence: mit
First seen on the Hub: 2022-03-02
Training datasets: samsum
samsum (reported): 60.0757
SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization (reported): 32.1337
Added to our catalog: 2026-07-28

Compare with any summarization model

Popular comparisons

bart-large-cnn 1.1 M distilbart-cnn-12-6 317 K long-t5-tglobal-base-sci-simplify 221 K T5-base-10K-summarization 84 K MEETING_SUMMARY 61 K pegasus-xsum 54 K