microsoft-deberta-large-mnli · azureml v9 ↗
- source model id
- azureml/microsoft-deberta-large-mnli@9
- hosting
- foundry-managed-compute
- platforms
- Microsoft Foundry
- license
- mit
- architecture
- input_modalities
- output_modalities
- capabilities
DeBERTa is an improvement of BERT and RoBERTa using disentangled attention and enhanced mask decoder. With 80GB training data, it outperforms BERT and RoBERTa on the majority of NLU tasks. The fine-t…
azureFoundry/azureml/microsoft-deberta-large-mnli@9
DeBERTa is an improvement of BERT and RoBERTa using disentangled attention and enhanced mask decoder. With 80GB training data, it outperforms BERT and RoBERTa on the majority of NLU tasks. The fine-tuned DeBERTa with MNLI task results in the best performance on SQuAD 1.1/2.0 and GLUE benchmark tasks. Further information is available in the official repository and the related paper.
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 | text-classification-online-endpoint.ipynb | <a href="https://aka.ms/azureml-infer-online-cli-text-classification" target="_blan |
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.