|
--- |
|
inference: false |
|
tags: |
|
- onnx |
|
- adapterhub:qa/narrativeqa |
|
- adapter-transformers |
|
- bart |
|
datasets: |
|
- narrativeqa |
|
--- |
|
|
|
# ONNX export of Adapter `AdapterHub/narrativeqa` for facebook/bart-base |
|
## Conversion of [AdapterHub/narrativeqa](https://huggingface.co/AdapterHub/narrativeqa) for UKP SQuARE |
|
|
|
|
|
## Usage |
|
```python |
|
onnx_path = hf_hub_download(repo_id='UKP-SQuARE/bart-base-pf-narrativeqa-onnx', filename='model.onnx') # or model_quant.onnx for quantization |
|
onnx_model = InferenceSession(onnx_path, providers=['CPUExecutionProvider']) |
|
|
|
context = 'ONNX is an open format to represent models. The benefits of using ONNX include interoperability of frameworks and hardware optimization.' |
|
question = 'What are advantages of ONNX?' |
|
tokenizer = AutoTokenizer.from_pretrained('UKP-SQuARE/bart-base-pf-narrativeqa-onnx') |
|
|
|
inputs = tokenizer(question, context, padding=True, truncation=True, return_tensors='np') |
|
outputs = onnx_model.run(input_feed=dict(inputs), output_names=None) |
|
``` |
|
|
|
## Architecture & Training |
|
|
|
<!-- Add some description here --> |
|
|
|
## Evaluation results |
|
|
|
<!-- Add some description here --> |
|
|
|
## Citation |
|
|
|
<!-- Add some description here --> |
