microsoft-deberta-base-mnli · azureml v3

DeBERTa is a version of the BERT model that has been improved through the use of disentangled attention and enhanced mask decoders. Compared to BERT and RoBERTa, it outperforms them on a majority of …

azureFoundry/azureml/microsoft-deberta-base-mnli@3

DeBERTa is a version of the BERT model that has been improved through the use of disentangled attention and enhanced mask decoders. Compared to BERT and RoBERTa, it outperforms them on a majority of NLU tasks using 80GB of training data. It has been fine-tuned for 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.

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 samples

Inference typePython sample (Notebook)CLI with YAML
Real timeentailment-contradiction-online.ipynb<a href="https://aka.ms/azureml-infer-online-cli-text-classification" target="_blank"

Specifications & capabilities

Provider specifications & access

1–1 / 1

Original sources

1–3 / 3

Microsoft Foundry · Model page ↗

Microsoft Foundry · Model documentation ↗

Microsoft Foundry · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

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.

Install TensorTrace