def __init__(self, model_path):
super(OnmtXLNetEncoder, self).__init__()
config = XLNetConfig.from_json_file(
os.path.join(model_path, "config.json"))
pretrained_dict = os.path.join(model_path, "pytorch_model.bin")
if os.path.exists(pretrained_dict):
model = XLNetModel.from_pretrained(
pretrained_model_name_or_path=pretrained_dict, config=config)
print("init XLNet model with {} weights".format(
len(model.state_dict())))
else:
model = XLNetModel(config)
model.word_embedding = expandEmbeddingByN(model.word_embedding, 4)
model.word_embedding = expandEmbeddingByN(model.word_embedding,
2,
last=True)
self.encoder = model
#print(model)
print("***" * 20)
def convert_xlnet_checkpoint_to_pytorch(tf_checkpoint_path,
bert_config_file,
pytorch_dump_folder_path,
finetuning_task=None):
# Initialise PyTorch model
config = XLNetConfig.from_json_file(bert_config_file)
finetuning_task = finetuning_task.lower(
) if finetuning_task is not None else ""
if finetuning_task in GLUE_TASKS_NUM_LABELS:
print(
"Building PyTorch XLNetForSequenceClassification model from configuration: {}"
.format(str(config)))
config.finetuning_task = finetuning_task
config.num_labels = GLUE_TASKS_NUM_LABELS[finetuning_task]
model = XLNetForSequenceClassification(config)
elif 'squad' in finetuning_task:
config.finetuning_task = finetuning_task
model = XLNetForQuestionAnswering(config)
else:
model = XLNetLMHeadModel(config)
# Load weights from tf checkpoint
load_tf_weights_in_xlnet(model, config, tf_checkpoint_path)
# Save pytorch-model
pytorch_weights_dump_path = os.path.join(pytorch_dump_folder_path,
WEIGHTS_NAME)
pytorch_config_dump_path = os.path.join(pytorch_dump_folder_path,
CONFIG_NAME)
print("Save PyTorch model to {}".format(
os.path.abspath(pytorch_weights_dump_path)))
torch.save(model.state_dict(), pytorch_weights_dump_path)
print("Save configuration file to {}".format(
os.path.abspath(pytorch_config_dump_path)))
with open(pytorch_config_dump_path, "w", encoding="utf-8") as f:
f.write(config.to_json_string())