bert-base-cased · azureml v7 ↗
- source model id
- azureml/bert-base-cased@7
- hosting
- foundry-managed-compute
- platforms
- Microsoft Foundry
- license
- apache-2.0
- architecture
- input_modalities
- output_modalities
- capabilities
The BERT model is a pre-trained model that has been trained on a large corpus of English language data. The model was trained using a masked language modeling (MLM) objective, meaning that the model …
azureFoundry/azureml/bert-base-cased@7
The BERT model is a pre-trained model that has been trained on a large corpus of English language data. The model was trained using a masked language modeling (MLM) objective, meaning that the model is able to predict words that were randomly masked in an input sentence. The BERT model can also predict if two sentences were originally consecutive in a text or not. This model is intended to be used as a tool for fine-tuning in various downstream tasks such as sequence classification and question answering, but is not recommended for tasks such as text generation. To use this model, you can utilize a pipeline specifically designed for masked language modeling.
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 use
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.