bert-large-uncased-whole-word-masking-squad2

这是一个berta-large模型，使用SQuAD2.0数据集进行了细粒度调整，用于问答任务。

概述

语言模型：bert-large 语言：英语 下游任务：抽取式问答 训练数据：SQuAD 2.0 评估数据：SQuAD 2.0 代码：查看 an example QA pipeline on Haystack

用法

在Haystack中

Haystack是由deepset开发的自然语言处理框架。您可以在Haystack流水线中使用此模型来批量进行问答（覆盖许多文档）。要在 Haystack 中加载该模型：

reader = FARMReader(model_name_or_path="deepset/bert-large-uncased-whole-word-masking-squad2")
# or 
reader = TransformersReader(model_name_or_path="FILL",tokenizer="deepset/bert-large-uncased-whole-word-masking-squad2")

在Transformers中

from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

model_name = "deepset/bert-large-uncased-whole-word-masking-squad2"

# 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)

关于我们

deepset 是开源的NLP框架 Haystack 的公司，旨在帮助您构建可用于生产的NLP系统，包括：问答、摘要、排名等。

我们的其他工作包括：

• Distilled roberta-base-squad2 (aka "tinyroberta-squad2")
• German BERT (aka "bert-base-german-cased")
• GermanQuAD and GermanDPR datasets and models (aka "gelectra-base-germanquad", "gbert-base-germandpr")

联系我们，加入Haystack社区

要了解有关Haystack的更多信息，请访问我们的 GitHub 存储库和 Documentation 。

我们还有一个 Discord community open to everyone!

Twitter | LinkedIn | Discord | GitHub Discussions | Website

顺便说一下： we're hiring!