deberta v3 large
简介
核心亮点
- NLU 任务顶尖性能，语义理解精度极高
- 支持微调，是构建高性能分类器的理想底座
- 推理开销远低于 LLM，适合高并发部署
- MIT 协议开源，商业化落地无压力
使用方法
# 安装 Hugging Face transformers
pip install transformers torch# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("microsoft/deberta-v3-large")
tokenizer = AutoTokenizer.from_pretrained("microsoft/deberta-v3-large")Hugging Face 下载
我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。
操作指引：在下载前，请先通过如下命令安装 huggingface_hub：
pip install -U huggingface_hub命令行下载
下载完整模型库
huggingface-cli download microsoft/deberta-v3-large下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）
huggingface-cli download microsoft/deberta-v3-large config.json --local-dir ./dirSDK 下载
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('microsoft/deberta-v3-large')Git 下载
请确保 lfs 已经被正确安装
git lfs install
git clone https://huggingface.co/microsoft/deberta-v3-large如果您希望跳过 lfs 大文件下载，可以使用如下命令
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/microsoft/deberta-v3-large模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。
PyTorch / Transformers 使用
安装 Transformers
pip install -U transformers torch模型加载和推理
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained('microsoft/deberta-v3-large')
tokenizer = AutoTokenizer.from_pretrained('microsoft/deberta-v3-large')模型下载
我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。
操作指引：在下载前，请先通过如下命令安装 ModelScope：
pip install modelscope命令行下载
下载完整模型库
modelscope download --model microsoft/deberta-v3-large下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例）
modelscope download --model microsoft/deberta-v3-large README.md --local_dir ./dirSDK 下载
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('microsoft/deberta-v3-large')Git 下载
请确保 lfs 已经被正确安装
git lfs install
git clone https://www.modelscope.cn/microsoft/deberta-v3-large.git如果您希望跳过 lfs 大文件下载，可以使用如下命令
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/microsoft/deberta-v3-large.gitModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。
Notebook 快速开发
下载并安装 ModelScope library
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html模型加载和推理
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
p = pipeline('text-generation', 'microsoft/deberta-v3-large')完整文档
---
language: en
tags:
- deberta
- deberta-v3
- fill-mask
thumbnail: https://huggingface.co/front/thumbnails/microsoft.png
license: mit
---
DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
DeBERTa improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. With those two improvements, DeBERTa out perform RoBERTa on a majority of NLU tasks with 80GB training data.
In DeBERTa V3, we further improved the efficiency of DeBERTa using ELECTRA-Style pre-training with Gradient Disentangled Embedding Sharing. Compared to DeBERTa, our V3 version significantly improves the model performance on downstream tasks. You can find more technique details about the new model from our paper.
Please check the official repository for more implementation details and updates.
The DeBERTa V3 large model comes with 24 layers and a hidden size of 1024. It has 304M backbone parameters with a vocabulary containing 128K tokens which introduces 131M parameters in the Embedding layer. This model was trained using the 160GB data as DeBERTa V2.
#### Fine-tuning on NLU tasks
We present the dev results on SQuAD 2.0 and MNLI tasks.
| Model |Vocabulary(K)|Backbone #Params(M)| SQuAD 2.0(F1/EM) | MNLI-m/mm(ACC)|
|-------------------|----------|-------------------|-----------|----------|
| RoBERTa-large |50 |304 | 89.4/86.5 | 90.2 |
| XLNet-large |32 |- | 90.6/87.9 | 90.8 |
| DeBERTa-large |50 |- | 90.7/88.0 | 91.3 |
| DeBERTa-v3-large|128|304 | 91.5/89.0| 91.8/91.9|
#### Fine-tuning with HF transformers
#!/bin/bash
cd transformers/examples/pytorch/text-classification/
pip install datasets
export TASK_NAME=mnli
output_dir="ds_results"
num_gpus=8
batch_size=8
python -m torch.distributed.launch --nproc_per_node=${num_gpus} \
run_glue.py \
--model_name_or_path microsoft/deberta-v3-large \
--task_name $TASK_NAME \
--do_train \
--do_eval \
--evaluation_strategy steps \
--max_seq_length 256 \
--warmup_steps 50 \
--per_device_train_batch_size ${batch_size} \
--learning_rate 6e-6 \
--num_train_epochs 2 \
--output_dir $output_dir \
--overwrite_output_dir \
--logging_steps 1000 \
--logging_dir $output_dir
Citation
If you find DeBERTa useful for your work, please cite the following papers:
`` latex``
@misc{he2021debertav3,
title={DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing},
author={Pengcheng He and Jianfeng Gao and Weizhu Chen},
year={2021},
eprint={2111.09543},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
@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}
}
