# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("xichenn/albert-base-v2-squad")
model = AutoModelForQuestionAnswering.from_pretrained("xichenn/albert-base-v2-squad", device_map="auto")Quick Links
albert-base-v2-squad
This model is a fine-tuned version of albert-base-v2 on the SQuAD 1.1 and adversarial_qa datasets. It achieves the following results on the SQuAD 1.1 evaluation set:
- Exact Match(EM): 84.68
- F1: 91.40
Inference API
You can test the model directly using the Hugging Face Inference API:
from transformers import pipeline
# Load the pipeline
qa_pipeline = pipeline("question-answering", model="xichenn/albert-base-v2-squad")
# Run inference
result = qa_pipeline(question="What is the capital of France?", context="France is a country in Europe. Its capital is Paris.")
print(result)
- Downloads last month
- 34
Model tree for xichenn/albert-base-v2-squad
Base model
albert/albert-base-v2Datasets used to train xichenn/albert-base-v2-squad
Evaluation results
- Exact Match on squadvalidation set self-reported84.680
- F1 on squadvalidation set self-reported91.400
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="xichenn/albert-base-v2-squad")