deepset-roberta-base-squad2 · azureml v7 ↗
- source model id
- azureml/deepset-roberta-base-squad2@7
- hosting
- foundry-managed-compute
- platforms
- Microsoft Foundry
- license
- cc-by-4.0
- architecture
- input_modalities
- text
- output_modalities
- text
- capabilities
Roberta-base is a fine-tuned language model for extractive Question Answering in English, trained on the SQuAD2.0 dataset. It is based on the "roberta-base" model, developed by deepset and can be use…
azureFoundry/azureml/deepset-roberta-base-squad2@7
Roberta-base is a fine-tuned language model for extractive Question Answering in English, trained on the SQuAD2.0 dataset. It is based on the "roberta-base" model, developed by deepset and can be used with Haystack and Transformers. The model requires 4 Tesla v100s and has a batch size of 96, 2 epochs, and a learning rate of 3e-5. The model was evaluated on the SQuAD 2.0 dev set and achieved an exact match of 79.87 and an F1 score of 82.91. There is also a distilled version of this model available called "deepset/tinyroberta-squad2" which has a comparable prediction quality and runs twice as fast. Usage examples for the model are provided for Haystack and Transformers. The authors of the model are Branden Chan, Timo Möller, Malte Pietsch, and Tanay Soni from deepset.ai.
The above summary was generated using ChatGPT. Review the original model card to understand the data used to train the model, evaluatio
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.