microsoft-deberta-base-mnli · azureml v16 ↗
- source model id
- azureml/microsoft-deberta-base-mnli@16
- hosting
- foundry-managed-compute
- platforms
- Microsoft Foundry
- license
- mit
- architecture
- input_modalities
- output_modalities
- capabilities
[DeBERTa](https://arxiv.org/abs/2006.03654) (Decoding-enhanced BERT with Disentangled Attention) improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. It outper…
azureFoundry/azureml/microsoft-deberta-base-mnli@16
DeBERTa (Decoding-enhanced BERT with Disentangled Attention) improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. It outperforms BERT and RoBERTa on majority of NLU tasks with 80GB training data.
Please check the official repository for more details and updates.
This model is the base DeBERTa model fine-tuned with MNLI task
We present the dev results on SQuAD 1.1/2.0 and MNLI tasks.
| Model | SQuAD 1.1 | SQuAD 2.0 | MNLI-m |
|---|---|---|---|
| RoBERTa-base | 91.5/84.6 | 83.7/80.5 | 87.6 |
| XLNet-Large | -/- | -/80.2 | 86.8 |
| DeBERTa-base | 93.1/87.2 | 86.2/83.1 | 88.8 |
| Task | Use case | Dataset | Python sample (Notebook) | CLI with YAML |
|---|---|---|---|---|
| Text Classification | Sentiment Classification | SST2 | evaluate-model-sentiment-analysis.ipynb | evaluate-model-sentiment-analysis.yml |
| Inference type | Python sample (Notebook) |
|---|---|
| Real time | sdk-example.ipynb |
| Real time | text-classification-online-endpoint.ipynb |
{
"input_data": [
"Today was an amazing day!",
"It was an unfortunate series of events."
]
}
[
{
"label": "NEUTRAL",
"score": 0.9817705750465393
},
{
"label": "NEUTRAL",
"score": 0.9873806238174438
}
]
1–1 / 1
1–3 / 3
Microsoft Foundry · Model page ↗
1–1 / 1
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.