SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Bart-CNN (#3059)

Browse Source 
`generate` code that produces 99% identical summarizations to fairseq on CNN test data, with caching.
This commit is contained in:
Sam Shleifer
2020-03-02 10:35:53 -05:00
committed by GitHub
parent 6b1ff25084
commit b54ef78d0c
8 changed files with 544 additions and 152 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/source/pretrained_models.rst
View File

@@ -280,7 +280,10 @@ For a list that includes community-uploaded models, refer to `https://huggingfac
| | | (see `details <https://github.com/pytorch/fairseq/tree/master/examples/bart>`_) |
| +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
| | ``bart-large-mnli`` | | Adds a 2 layer classification head with 1 million parameters |
| | | | bart-large base architecture with a classification head |
| | | | bart-large base architecture with a classification head, finetuned on MNLI |
| +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
| | ``bart-large-cnn`` | | 12-layer, 1024-hidden, 16-heads, 406M parameters (same as base) |
| | | | bart-large base architecture finetuned on cnn summarization task |
+-------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+