AlgorithmicResearchGroup
/

led_base_16384_arxiv_summarization

text2text-generation

Eval Results (legacy)

Model card Files Files and versions

Artifact AI commited on Oct 17, 2022

Commit

bdde97a

·

1 Parent(s): 86117e1

update readme

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ A led-base-16384 model to summarize ArXiv papers. Inputs are the abstracts of pa
 As described in [Longformer: The Long-Document Transformer](https://arxiv.org/pdf/2004.05150.pdf) by Iz Beltagy, Matthew E. Peters, Arman Cohan, *led-base-16384* was initialized from [*bart-base*](https://huggingface.co/facebook/bart-base) since both models share the exact same architecture. To be able to process 16K tokens, *bart-base*'s position embedding matrix was simply copied 16 times.
-### Rouge
 | Type | Score |
 | --- | --- |

 As described in [Longformer: The Long-Document Transformer](https://arxiv.org/pdf/2004.05150.pdf) by Iz Beltagy, Matthew E. Peters, Arman Cohan, *led-base-16384* was initialized from [*bart-base*](https://huggingface.co/facebook/bart-base) since both models share the exact same architecture. To be able to process 16K tokens, *bart-base*'s position embedding matrix was simply copied 16 times.
+### Rouge 2
 | Type | Score |
 | --- | --- |