给定一个前提句和一个假设句,任务是预测前提是否包含假设(蕴含),与假设相矛盾(矛盾),或者两者都不包含(中性)。
玩转OFA只需区区以下数行代码,就是如此轻松!如果你觉得还不够方便,请点击右上角Notebook
按钮,我们为你提供了配备好的环境(可选CPU/GPU),你只需要在notebook里输入提供的代码,就可以把OFA玩起来了!
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
ofa_pipe = pipeline(
Tasks.text_classification,
model='damo/ofa_text-classification_mnli_large_en',
model_revision='v1.0.1'
)
text = 'One of our number will carry out your instructions minutely.'
text2 = 'A member of my team will execute your orders with immense precision.'
input = {'text': text, 'text2': text2}
result = ofa_pipe(input)
print(result)
OFA(One-For-All)是通用多模态预训练模型,使用简单的序列到序列的学习框架统一模态(跨模态、视觉、语言等模态)和任务(如图片生成、视觉定位、图片描述、图片分类、文本生成等),详见我们发表于ICML 2022的论文:OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework,以及我们的官方Github仓库https://github.com/OFA-Sys/OFA。
Github  |  Paper   |  Blog
Model | Params-en | Params-zh | Backbone | Hidden size | Intermediate size | Num. of heads | Enc layers | Dec layers |
---|---|---|---|---|---|---|---|---|
OFATiny | 33M | - | ResNet50 | 256 | 1024 | 4 | 4 | 4 |
OFAMedium | 93M | - | ResNet101 | 512 | 2048 | 8 | 4 | 4 |
OFABase | 180M | 160M | ResNet101 | 768 | 3072 | 12 | 6 | 6 |
OFALarge | 470M | 440M | ResNet152 | 1024 | 4096 | 16 | 12 | 12 |
OFAHuge | 930M | - | ResNet152 | 1280 | 5120 | 16 | 24 | 12 |
OFA在GLUE多个任务上取得了和RoBERTa、DEBERTa等经典模型匹敌的结果,具体如下所示:
本模型训练数据集是glue/mnli数据集。
模型及finetune细节请参考OFA Tutorial 1.4节。
from modelscope.msdatasets import MsDataset
import tempfile
from modelscope.msdatasets import MsDataset
from modelscope.metainfo import Trainers
from modelscope.trainers import build_trainer
from modelscope.utils.constant import DownloadMode
train_dataset = MsDataset(
MsDataset.load('clue', subset_name='afqmc', split='train').remap_columns({
'sentence1': 'text',
'sentence2': 'text2'
}))
test_dataset = MsDataset(
MsDataset.load('clue', subset_name='afqmc', split='validation').remap_columns({
'sentence1': 'text',
'sentence2': 'text2'
}))
def cfg_modify_fn(cfg):
cfg.train.hooks = [{
'type': 'CheckpointHook',
'interval': 2
}, {
'type': 'TextLoggerHook',
'interval': 1
}, {
'type': 'IterTimerHook'
}]
cfg.train.max_epochs=2
return cfg
args = dict(
model='damo/ofa_text-classification_mnli_large_en',
model_revision='v1.0.1',
train_dataset=train_dataset,
eval_dataset=test_dataset,
cfg_modify_fn=cfg_modify_fn,
work_dir = tempfile.TemporaryDirectory().name)
trainer = build_trainer(name=Trainers.ofa, default_args=args)
trainer.train()
训练数据集自身有局限,有可能产生一些偏差,请用户自行评测后决定如何使用。
如果你觉得OFA好用,喜欢我们的工作,欢迎引用:
@article{wang2022ofa,
author = {Peng Wang and
An Yang and
Rui Men and
Junyang Lin and
Shuai Bai and
Zhikang Li and
Jianxin Ma and
Chang Zhou and
Jingren Zhou and
Hongxia Yang},
title = {OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence
Learning Framework},
journal = {CoRR},
volume = {abs/2202.03052},
year = {2022}
}