Bart Large Finetuned Squad2

🚀 roberta-large-finetuned-squad2

本模型基于facebook/bart-large在SQuAD2.0数据集上进行微调，可用于问答任务。它能帮助用户在给定的上下文中准确找到问题的答案，在问答领域具有较高的应用价值。

🚀 快速开始

模型描述

该模型基于 facebook/bart-large 构建，并在 SQuAD2.0 数据集上进行了微调。相关论文可在 此处（模型） 和 此处（数据） 找到。

模型信息

💻 使用示例

基础用法

from transformers.pipelines import pipeline

model_name = "phiyodr/bart-large-finetuned-squad2"
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
inputs = {
    'question': 'What discipline did Winkelmann create?',
    'context': 'Johann Joachim Winckelmann was a German art historian and archaeologist. He was a pioneering Hellenist who first articulated the difference between Greek, Greco-Roman and Roman art. "The prophet and founding hero of modern archaeology", Winckelmann was one of the founders of scientific archaeology and first applied the categories of style on a large, systematic basis to the history of art. '
}
nlp(inputs)

🔧 技术细节

训练过程

{
    "base_model": "facebook/bart-large",
    "do_lower_case": True,
    "learning_rate": 3e-5,
    "num_train_epochs": 4,
    "max_seq_length": 384,
    "doc_stride": 128,
    "max_query_length": 64,
    "batch_size": 96 
}

评估结果

• 数据：dev-v2.0.json
• 脚本：evaluate-v2.0.py （原始脚本来自 此处）

{
    "exact": 81.96748926134929,
    "f1": 85.93825235371045,
    "total": 11873,
    "HasAns_exact": 78.71120107962213,
    "HasAns_f1": 86.6641144054667,
    "HasAns_total": 5928,
    "NoAns_exact": 85.21446593776282,
    "NoAns_f1": 85.21446593776282,
    "NoAns_total": 5945
}