Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
chenpangpang
transformers
Commits
f8823bad
Commit
f8823bad
authored
Mar 24, 2020
by
Julien Chaumond
Browse files
Expose missing mappings (see #3415)
parent
d0c36a7b
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
10 additions
and
6 deletions
+10
-6
examples/run_language_modeling.py
examples/run_language_modeling.py
+8
-4
src/transformers/__init__.py
src/transformers/__init__.py
+2
-2
No files found.
examples/run_language_modeling.py
View file @
f8823bad
...
...
@@ -38,7 +38,6 @@ from torch.utils.data.distributed import DistributedSampler
from
tqdm
import
tqdm
,
trange
from
transformers
import
(
CONFIG_MAPPING
,
MODEL_WITH_LM_HEAD_MAPPING
,
WEIGHTS_NAME
,
AdamW
,
...
...
@@ -679,7 +678,12 @@ def main():
elif
args
.
model_name_or_path
:
config
=
AutoConfig
.
from_pretrained
(
args
.
model_name_or_path
,
cache_dir
=
args
.
cache_dir
)
else
:
config
=
CONFIG_MAPPING
[
args
.
model_type
]()
# When we release a pip version exposing CONFIG_MAPPING,
# we can do `config = CONFIG_MAPPING[args.model_type]()`.
raise
ValueError
(
"You are instantiating a new config instance from scratch. This is not supported, but you can do it from another script, save it,"
"and load it from here, using --config_name"
)
if
args
.
tokenizer_name
:
tokenizer
=
AutoTokenizer
.
from_pretrained
(
args
.
tokenizer_name
,
cache_dir
=
args
.
cache_dir
)
...
...
@@ -687,8 +691,8 @@ def main():
tokenizer
=
AutoTokenizer
.
from_pretrained
(
args
.
model_name_or_path
,
cache_dir
=
args
.
cache_dir
)
else
:
raise
ValueError
(
"You are instantiating a new
{}
tokenizer. This is not supported, but you can do it from another script, save it,"
"and load it from here, using --tokenizer_name"
.
format
(
AutoTokenizer
.
__name__
)
"You are instantiating a new tokenizer
from scratch
. This is not supported, but you can do it from another script, save it,"
"and load it from here, using --tokenizer_name"
)
if
args
.
block_size
<=
0
:
...
...
src/transformers/__init__.py
View file @
f8823bad
...
...
@@ -32,7 +32,7 @@ from .benchmark_utils import (
stop_memory_tracing
,
)
from
.configuration_albert
import
ALBERT_PRETRAINED_CONFIG_ARCHIVE_MAP
,
AlbertConfig
from
.configuration_auto
import
ALL_PRETRAINED_CONFIG_ARCHIVE_MAP
,
AutoConfig
from
.configuration_auto
import
ALL_PRETRAINED_CONFIG_ARCHIVE_MAP
,
CONFIG_MAPPING
,
AutoConfig
from
.configuration_bart
import
BartConfig
from
.configuration_bert
import
BERT_PRETRAINED_CONFIG_ARCHIVE_MAP
,
BertConfig
from
.configuration_camembert
import
CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP
,
CamembertConfig
...
...
@@ -119,7 +119,7 @@ from .pipelines import (
pipeline
,
)
from
.tokenization_albert
import
AlbertTokenizer
from
.tokenization_auto
import
AutoTokenizer
from
.tokenization_auto
import
TOKENIZER_MAPPING
,
AutoTokenizer
from
.tokenization_bart
import
BartTokenizer
from
.tokenization_bert
import
BasicTokenizer
,
BertTokenizer
,
BertTokenizerFast
,
WordpieceTokenizer
from
.tokenization_bert_japanese
import
BertJapaneseTokenizer
,
CharacterTokenizer
,
MecabTokenizer
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment