microsoft-deberta-base · azureml v8 ↗
- source model id
- azureml/microsoft-deberta-base@8
- hosting
- foundry-managed-compute
- platforms
- Microsoft Foundry
- license
- mit
- architecture
- input_modalities
- output_modalities
- capabilities
DeBERTa is a version of the BERT model that has been improved through the use of disentangled attention and enhanced mask decoders. It outperforms BERT and RoBERTa on a majority of NLU tasks using 80…
azureFoundry/azureml/microsoft-deberta-base@8
DeBERTa is a version of the BERT model that has been improved through the use of disentangled attention and enhanced mask decoders. It outperforms BERT and RoBERTa on a majority of NLU tasks using 80GB of training data. It has been fine-tuned on NLU tasks and has achieved dev results on SQuAD 1.1/2.0 and MNLI tasks.If you find the model useful please cite the paper.
Please check the official repository for more detailed updates.
Please Note: This model accepts masks in [mask] format. See Sample input for reference.
The above summary was generated using ChatGPT. Review the original model card to understand the data used to train the model, evaluation metrics, license, intended uses, limitations and bias before using the model.
| Inference type | Python sample (Notebook) | CLI with YAML |
|---|---|---|
| Real time | fil |
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.