🤖 question-answering

bert-medium-squad2-distilled

deepset/bert-medium-squad2-distilled

Get AI Model →
113.1K
Downloads
❤️
4
Likes
🏷️
13
Tags
📦
transformers
Library
Model Details
Full Model IDdeepset/bert-medium-squad2-distilled
Pipeline / Taskquestion-answering
Librarytransformers
Downloads (all-time)113.1K
Likes4
Last Modified9/24/2024
Author / Orgdeepset
PrivateNo — public
⚡ Quick Usage (Python)

Using the 🤗 Transformers library. Install with pip install transformers

from transformers import pipeline

# Load the model
pipe = pipeline("question-answering", model="deepset/bert-medium-squad2-distilled")

# Run inference
result = pipe("Your input here")
print(result)
🏷️ Tags
transformerspytorchsafetensorsbertquestion-answeringexbertendataset:squad_v2license:mitmodel-indexendpoints_compatibledeploy:azureregion:us
More question-answering Models
See all →
electra_large_discriminator_squad2_512

ahotrod/electra_large_discriminator_squad2_512

888.7K❤️ 7
Get AI Model →
roberta-base-squad2

deepset/roberta-base-squad2

512.2K❤️ 946
Get AI Model →
mdeberta-v3-base-squad2

timpal0l/mdeberta-v3-base-squad2

288.4K❤️ 259
Get AI Model →
🚀 Use This Model

Access model files, inference API, and full documentation on Hugging Face.

Open on Hugging Face →Browse Model Files ↗← Browse All Models
🤖 Task: question-answering

This model is designed for the question-answering task. Explore more models for this use case.

All question-answering Models →
📊 Popularity
Downloads113.1K
❤️ Community Likes4
🛠️ Requirements
  • Install: pip install transformers
  • Python 3.8+ recommended for Transformers.
  • GPU (CUDA) speeds up inference significantly.
  • Use model.half() for fp16 on limited VRAM.
👋 Need help with code?