DeBERTa improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. It outperforms BERT and RoBERTa on majority of NLU tasks with 80GB training data.
Please check the official repository for more details and updates.
We present the dev results on SQuAD 1.1/2.0 and MNLI tasks.
| Model | SQuAD 1.1 | SQuAD 2.0 | MNLI-m |
|---|---|---|---|
| RoBERTa-base | 91.5/84.6 | 83.7/80.5 | 87.6 |
| XLNet-Large | -/- | -/80.2 | 86.8 |
| DeBERTa-base | 93.1/87.2 | 86.2/83.1 | 88.8 |
from openmind import AutoTokenizer, AutoModel, is_torch_npu_available
from openmind_hub import snapshot_download
import torch.nn.functional as F
from torch import Tensor
import openmind
import torch
import argparse
import time
# Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] # First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument(
"--model_name_or_path",
type=str,
help="Path to model",
default="jeffding/deberta-base-openmind",
)
args = parser.parse_args()
return args
def main():
args = parse_args()
model_path = args.model_name_or_path
if is_torch_npu_available():
device = "npu:0"
else:
device = "cpu"
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained(model_path,trust_remote_code=True)
model = AutoModel.from_pretrained(model_path, trust_remote_code=True).to(device)
start_time = time.time()
sentences = ['如何更换花呗绑定银行卡', 'How to replace the Huabei bundled bank card']
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt').to(device)
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
end_time = time.time()
print(f"硬件环境:{device},推理执行时间:{end_time - start_time}秒")
if __name__ == "__main__":
main()If you find DeBERTa useful for your work, please cite the following paper:
@inproceedings{
he2021deberta,
title={DEBERTA: DECODING-ENHANCED BERT WITH DISENTANGLED ATTENTION},
author={Pengcheng He and Xiaodong Liu and Jianfeng Gao and Weizhu Chen},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=XPZIaotutsD}
}