Bert Base Finetuned Squad2

🚀 bert-base-finetuned-squad2

本模型基於BERT架構進行微調，專門用於處理問答任務，能夠在給定的上下文中準確找出問題的答案，在SQuAD2.0數據集上有出色的表現。

🚀 快速開始

本模型基於 bert-base-uncased ，並在 SQuAD2.0 數據集上進行了微調。你可以在 這裡（模型） 和 這裡（數據） 找到相應的論文。

✨ 主要特性

• 標籤：pytorch、question-answering
• 數據集：squad2
• 評估指標：exact、f1

📦 安裝指南

文檔未提及安裝步驟，可參考Hugging Face Transformers庫的安裝方式。

💻 使用示例

基礎用法

from transformers.pipelines import pipeline

model_name = "phiyodr/bert-base-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)

🔧 技術細節

訓練流程

{
    "base_model": "bert-base-uncased",
    "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 
}

評估結果

• 數據：dev-v2.0.json
• 腳本：evaluate-v2.0.py （原始腳本來自 這裡）

{
  "exact": 70.3950138970774,
  "f1": 73.90527661873521,
  "total": 11873,
  "HasAns_exact": 71.4574898785425,
  "HasAns_f1": 78.48808186475087,
  "HasAns_total": 5928,
  "NoAns_exact": 69.33557611438184,
  "NoAns_f1": 69.33557611438184,
  "NoAns_total": 5945
}

📄 許可證

文檔未提及許可證信息。