deepset/xlm-roberta-base-squad2-distilled

使用了Haystack的蒸馏功能进行训练。使用了deepset/xlm-roberta-large-squad2作为教师模型。

概述

语言模型：deepset/xlm-roberta-base-squad2-distilled 语言：多语种下游任务：抽取型问答训练数据：SQuAD 2.0 评估数据：SQuAD 2.0 代码：请参见 an example QA pipeline on Haystack 基础设施：1x Tesla v100

超参数

batch_size = 56
n_epochs = 4
max_seq_len = 384
learning_rate = 3e-5
lr_schedule = LinearWarmup
embeds_dropout_prob = 0.1
temperature = 3
distillation_loss_weight = 0.75

使用方法

在Haystack中

Haystack是一个由deepset开发的NLP框架。您可以在Haystack流程中使用此模型，在许多文档上进行大规模的问答。将模型加载到 Haystack 中：

reader = FARMReader(model_name_or_path="deepset/xlm-roberta-base-squad2-distilled")
# or 
reader = TransformersReader(model_name_or_path="deepset/xlm-roberta-base-squad2-distilled",tokenizer="deepset/xlm-roberta-base-squad2-distilled")

有关deepset/xlm-roberta-base-squad2-distilled用于[问答]的完整示例，请查看 Tutorials in Haystack Documentation

在Transformers中

from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

model_name = "deepset/xlm-roberta-base-squad2-distilled"

# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
    'question': 'Why is model conversion important?',
    'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)

# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

性能

在SQuAD 2.0开发集上进行评估

"exact": 74.06721131980123%
"f1": 76.39919553344667%

作者

Timo Möller: timo.moeller@deepset.ai Julian Risch: julian.risch@deepset.ai Malte Pietsch: malte.pietsch@deepset.ai Michel Bartels: michel.bartels@deepset.ai