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

Merge pull request #2189 from stefan-it/xlmr

Browse Source 
Add support for XLM-RoBERTa
This commit is contained in:
Thomas Wolf
2019-12-20 13:26:38 +01:00
committed by GitHub
parent ff36e6d8d7 3376adc051
commit 59941c5d1f
12 changed files with 567 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
examples/run_glue.py
View File

@@ -52,6 +52,9 @@ from transformers import (WEIGHTS_NAME, BertConfig,
AlbertConfig,
AlbertForSequenceClassification,
AlbertTokenizer,
XLMRobertaConfig,
XLMRobertaForSequenceClassification,
XLMRobertaTokenizer,
)
from transformers import AdamW, get_linear_schedule_with_warmup
@@ -72,7 +75,8 @@ MODEL_CLASSES = {
'xlm': (XLMConfig, XLMForSequenceClassification, XLMTokenizer),
'roberta': (RobertaConfig, RobertaForSequenceClassification, RobertaTokenizer),
'distilbert': (DistilBertConfig, DistilBertForSequenceClassification, DistilBertTokenizer),
'albert': (AlbertConfig, AlbertForSequenceClassification, AlbertTokenizer)
'albert': (AlbertConfig, AlbertForSequenceClassification, AlbertTokenizer),
'xlmroberta': (XLMRobertaConfig, XLMRobertaForSequenceClassification, XLMRobertaTokenizer),
}
@@ -304,9 +308,9 @@ def load_and_cache_examples(args, task, tokenizer, evaluate=False):
else:
logger.info("Creating features from dataset file at %s", args.data_dir)
label_list = processor.get_labels()
if task in ['mnli', 'mnli-mm'] and args.model_type in ['roberta']:
if task in ['mnli', 'mnli-mm'] and args.model_type in ['roberta', 'xlmroberta']:
# HACK(label indices are swapped in RoBERTa pretrained model)
label_list[1], label_list[2] = label_list[2], label_list[1]
label_list[1], label_list[2] = label_list[2], label_list[1]
examples = processor.get_dev_examples(args.data_dir) if evaluate else processor.get_train_examples(args.data_dir)
features = convert_examples_to_features(examples,
tokenizer,

5
examples/run_ner.py
View File

@@ -38,11 +38,13 @@ from transformers import WEIGHTS_NAME, BertConfig, BertForTokenClassification, B
from transformers import RobertaConfig, RobertaForTokenClassification, RobertaTokenizer
from transformers import DistilBertConfig, DistilBertForTokenClassification, DistilBertTokenizer
from transformers import CamembertConfig, CamembertForTokenClassification, CamembertTokenizer
from transformers import XLMRobertaConfig, XLMRobertaForTokenClassification, XLMRobertaTokenizer
logger = logging.getLogger(__name__)
ALL_MODELS = sum(
(tuple(conf.pretrained_config_archive_map.keys()) for conf in (BertConfig, RobertaConfig, DistilBertConfig)),
(tuple(conf.pretrained_config_archive_map.keys()) for conf in (BertConfig, RobertaConfig, DistilBertConfig,
CamembertConfig, XLMRobertaConfig)),
())
MODEL_CLASSES = {
@@ -50,6 +52,7 @@ MODEL_CLASSES = {
"roberta": (RobertaConfig, RobertaForTokenClassification, RobertaTokenizer),
"distilbert": (DistilBertConfig, DistilBertForTokenClassification, DistilBertTokenizer),
"camembert": (CamembertConfig, CamembertForTokenClassification, CamembertTokenizer),
"xlmroberta": (XLMRobertaConfig, XLMRobertaForTokenClassification, XLMRobertaTokenizer),
}