metadata
license: apache-2.0
datasets:
- squad
- adversarial_qa
language:
- en
metrics:
- exact_match
- f1
base_model:
- albert/albert-base-v2
model: xichenn/albert-base-v2-squad-fp16
library_name: transformers
model-index:
- name: xichenn/albert-base-v2-squad-fp16
results:
- task:
type: question-answering
name: Question Answering
dataset:
name: squad
type: squad
config: plain_text
split: validation
metrics:
- type: exact_match
value: 84.68
name: Exact Match
verified: true
- type: f1
value: 91.4
name: F1
verified: true
albert-base-v2-squad-fp16
This model is a fp16 quantized version of albert-base-v2-squad. It achieves the following results on the SQuAD 1.1 evaluation set (no model accuracy loss compared to fp32):
- 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-fp16")
# 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)