distilbert-base-cased · azureml v4 ↗
- source model id
- azureml/distilbert-base-cased@4
- hosting
- foundry-managed-compute
- platforms
- Microsoft Foundry
- license
- apache-2.0
- architecture
- input_modalities
- output_modalities
- capabilities
The DistilBERT model is a smaller, faster version of the BERT model for Transformer-based language modeling with 40% fewer parameters and 60% faster run time while retaining 95% of BERT's performance…
azureFoundry/azureml/distilbert-base-cased@4
The DistilBERT model is a smaller, faster version of the BERT model for Transformer-based language modeling with 40% fewer parameters and 60% faster run time while retaining 95% of BERT's performance on the GLUE language understanding benchmark. This English language question answering model has a F1 score of 87.1 on SQuAD v1.1 and was developed by Hugging Face under the Apache 2.0 license. Training the model requires significant computational power, such as 8 16GB V100 GPUs and 90 hours. Intended uses include fine-tuning on downstream tasks, but it should not be used to create hostile or alienating environments and limitations and biases should be taken into account.
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, licen
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.