distilbert-base-cased · azureml v1 ↗
- source model id
- azureml/distilbert-base-cased@1
- 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@1
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.
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 (Not
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.