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

update tokenizer - update squad example for xlnet

Browse Source
This commit is contained in:
thomwolf
2019-07-15 17:30:42 +02:00
parent 3b469cb422
commit 15d8b1266c
20 changed files with 191 additions and 131 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
examples/run_glue.py
View File

@@ -242,7 +242,7 @@ def load_and_cache_examples(args, task, tokenizer, evaluate=False):
# Load data features from cache or dataset file
cached_features_file = os.path.join(args.data_dir, 'cached_{}_{}_{}_{}'.format(
'dev' if evaluate else 'train',
list(filter(None, args.model_name.split('/'))).pop(),
list(filter(None, args.model_name_or_path.split('/'))).pop(),
str(args.max_seq_length),
str(task)))
if os.path.exists(cached_features_file):
@@ -282,8 +282,10 @@ def main():
## Required parameters
parser.add_argument("--data_dir", default=None, type=str, required=True,
help="The input data dir. Should contain the .tsv files (or other data files) for the task.")
parser.add_argument("--model_name", default=None, type=str, required=True,
help="Bert/XLNet/XLM pre-trained model selected in the list: " + ", ".join(ALL_MODELS))
parser.add_argument("--model_type", default=None, type=str, required=True,
help="Model type selected in the list: " + ", ".join(MODEL_CLASSES.keys()))
parser.add_argument("--model_name_or_path", default=None, type=str, required=True,
help="Path to pre-trained model or shortcut name selected in the list: " + ", ".join(ALL_MODELS))
parser.add_argument("--task_name", default=None, type=str, required=True,
help="The name of the task to train selected in the list: " + ", ".join(processors.keys()))
parser.add_argument("--output_dir", default=None, type=str, required=True,
@@ -400,15 +402,11 @@ def main():
if args.local_rank not in [-1, 0]:
torch.distributed.barrier() # Make sure only the first process in distributed training will download model & vocab
args.model_type = ""
for key in MODEL_CLASSES:
if key in args.model_name.lower():
args.model_type = key # take the first match in model types
break
args.model_type = args.model_type.lower()
config_class, model_class, tokenizer_class = MODEL_CLASSES[args.model_type]
config = config_class.from_pretrained(args.config_name if args.config_name else args.model_name, num_labels=num_labels, finetuning_task=args.task_name)
tokenizer = tokenizer_class.from_pretrained(args.tokenizer_name if args.tokenizer_name else args.model_name, do_lower_case=args.do_lower_case)
model = model_class.from_pretrained(args.model_name, from_tf=bool('.ckpt' in args.model_name), config=config)
config = config_class.from_pretrained(args.config_name if args.config_name else args.model_name_or_path, num_labels=num_labels, finetuning_task=args.task_name)
tokenizer = tokenizer_class.from_pretrained(args.tokenizer_name if args.tokenizer_name else args.model_name_or_path, do_lower_case=args.do_lower_case)
model = model_class.from_pretrained(args.model_name_or_path, from_tf=bool('.ckpt' in args.model_name_or_path), config=config)
if args.local_rank == 0:
torch.distributed.barrier() # Make sure only the first process in distributed training will download model & vocab