Intel/qa_sparse_bert

Update requirements.txt

Update README.md

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update requirements.txt

Update requirements.txt

Update requirements.txt

Update requirements.txt

Update app.py

sparse only with pipeline

trying without distilbert model

add onnx

neural_compressor

optimum intel

back to the original

made intel model public

distilbert model instead

sparse answer

no picture

inputs fix

adding dense model

description expanded to include efficient deployment

correcting example

examples included

description updated

bigger context box

gradio inputs outputs

text box

no interface for now

inputs outputs for context

torch not pytorch

pytorch tensorflow to reqs

requirements with transformers

testing prediction

app coming soon

Add initial application file

initial commit