riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-30 17:52:35 +06:00
Code Issues Actions 30 Packages Projects Releases Wiki Activity

Add bart-base (#5014)

Browse Source
This commit is contained in:
Sam Shleifer 2020-06-15 13:29:26 -04:00 committed by GitHub
parent 7b685f5229
commit a9f1fc6c94
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 20 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/pretrained_models.rst
View File

@ -278,6 +278,8 @@ For a list that includes community-uploaded models, refer to `https://huggingfac
| Bart | ``facebook/bart-large`` | | 24-layer, 1024-hidden, 16-heads, 406M parameters |
| | | (see `details <https://github.com/pytorch/fairseq/tree/master/examples/bart>`_) |
| +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
| | ``facebook/bart-base`` | | 12-layer, 768-hidden, 16-heads, 139M parameters |
| +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
| | ``facebook/bart-large-mnli`` | | Adds a 2 layer classification head with 1 million parameters |
| | | | bart-large base architecture with a classification head, finetuned on MNLI |
| +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+

1
src/transformers/tokenization_bart.py
View File

@ -28,6 +28,7 @@ logger = logging.getLogger(__name__)
vocab_url = "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-vocab.json"
merges_url = "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-merges.txt"
_all_bart_models = [
"facebook/bart-base",
"facebook/bart-large",
"facebook/bart-large-mnli",
"facebook/bart-large-cnn",

17
tests/test_modeling_bart.py
View File

@ -40,6 +40,7 @@ if is_torch_available():
BartTokenizer,
MBartTokenizer,
BatchEncoding,
pipeline,
)
from transformers.modeling_bart import (
BART_PRETRAINED_MODEL_ARCHIVE_LIST,
@ -565,6 +566,22 @@ class BartModelIntegrationTests(unittest.TestCase):
)
self.assertTrue(torch.allclose(output[:, :3, :3], expected_slice, atol=TOLERANCE))
@slow
def test_bart_base_mask_filling(self):
pbase = pipeline(task="fill-mask", model="facebook/bart-base")
src_text = [" I went to the <mask>."]
results = [x["token_str"] for x in pbase(src_text)]
expected_results = ["Ġbathroom", "Ġrestroom", "Ġhospital", "Ġkitchen", "Ġcar"]
self.assertListEqual(results, expected_results)
@slow
def test_bart_large_mask_filling(self):
pbase = pipeline(task="fill-mask", model="facebook/bart-large")
src_text = [" I went to the <mask>."]
results = [x["token_str"] for x in pbase(src_text)]
expected_results = ["Ġbathroom", "Ġgym", "Ġwrong", "Ġmovies", "Ġhospital"]
self.assertListEqual(results, expected_results)
@slow
def test_mnli_inference(self):