from transformers import pipeline

# Load the model
qa_pipeline = pipeline(
    "question-answering",
    model="takumi123xxx/qa-model-hello-world"
)

# Use the model
context = "Tokyo is the capital city of Japan. Tokyo was originally a fishing village named Edo."
question = "What was Tokyo originally called?"

result = qa_pipeline(question=question, context=context)
print(f"Answer: {result['answer']}")
print(f"Score: {result['score']}")

Training Data

The model was fine-tuned on a custom dataset containing various question-answer pairs about general knowledge topics.

Inference API

This model supports the Hugging Face Inference API. You can use it directly through the API widget on this page or programmatically:

python

from huggingface_hub import InferenceClient

client = InferenceClient()
result = client.question_answering(
    question="What was Tokyo originally called?",
    context="Tokyo is the capital city of Japan. Tokyo was originally a fishing village named Edo.",
    model="takumi123xxx/qa-model-hello-world"
)

Performance

The model achieves high confidence scores (>0.99) on the training examples.