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

New BartModel (#2745)

Browse Source 
* Results same as fairseq
* Wrote a ton of tests
* Struggled with api signatures
* added some docs
This commit is contained in:
Sam Shleifer
2020-02-20 18:11:13 -05:00
committed by GitHub
parent 564fd75d65
commit 53ce3854a1
20 changed files with 1766 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/source/pretrained_models.rst
View File

@@ -275,6 +275,13 @@ For a list that includes community-uploaded models, refer to `https://huggingfac
| | | | FlauBERT large architecture |
| | | (see `details <https://github.com/getalp/Flaubert>`__) |
+-------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
+-------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
| Bart | ``bart-large`` | | 12-layer, 1024-hidden, 16-heads, 406M parameters |
| | | (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 |
+-------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
.. <https://huggingface.co/transformers/examples.html>`__