bert-qa-finetuned

BERT-base uncased fine-tuned on SQuAD v2

Model Details

Model Description

This model is a fine-tuned version of BERT-base uncased on the SQuAD v2 dataset for extractive question answering.
It was trained for 3 epochs and can answer questions given a context passage, while also handling unanswerable questions (a key feature of SQuAD v2).

• Developed by: Your Name
• Model type: Extractive Question Answering
• Language(s): English
• License: Apache-2.0
• Finetuned from: bert-base-uncased

Model Sources

• Dataset: SQuAD v2
• Base model: bert-base-uncased

---

Uses

Direct Use

• Extractive Question Answering: Given a passage and a question, the model extracts the most likely span of text that answers the question.
• Handles unanswerable questions by predicting "no answer" when appropriate.

Downstream Use

• Can be integrated into chatbots, virtual assistants, or search systems that require question answering over text.

Out-of-Scope Use

• Generative question answering (the model cannot generate new answers).
• Non-English tasks (the model was trained only on English data).

---

Bias, Risks, and Limitations

• The model inherits biases from the SQuAD v2 dataset.
• Performance may degrade on domain-specific or noisy text not represented in SQuAD v2.
• Not designed for open-domain QA across large corpora — works best when the context passage is provided.

---

How to Get Started with the Model

You can try the model with the following code:

from transformers import pipeline

qa_pipeline = pipeline("question-answering", model="peeyush01/bert-squad-v2")
result = qa_pipeline({
    "context": "Hugging Face is creating a tool that democratizes AI.",
    "question": "What is Hugging Face creating?"
})
print(result)

---

Author Details

• Peeyush
• Github : Github