models deepset roberta base squad2

deepset-roberta-base-squad2

Overview

Description: 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, evaluation metrics, license, intended uses, limitations and bias before using the model. ### Inference samples Inference type|Python sample (Notebook)|CLI with YAML |--|--|--| Real time|question-answering-online-endpoint.ipynb|question-answering-online-endpoint.sh Batch |question-answering-batch-endpoint.ipynb| coming soon ### Finetuning samples Task|Use case|Dataset|Python sample (Notebook)|CLI with YAML |--|--|--|--|--| Text Classification|Emotion Detection|Emotion|emotion-detection.ipynb|emotion-detection.sh Token Classification|Named Entity Recognition|Conll2003|named-entity-recognition.ipynb|named-entity-recognition.sh Question Answering|Extractive Q&A|SQUAD (Wikipedia)|extractive-qa.ipynb|extractive-qa.sh ### Model Evaluation Task|Use case|Dataset|Python sample (Notebook)|CLI with YAML |--|--|--|--|--| Question Answering|Extractive Q&A|Squad v2|evaluate-model-question-answering.ipynb|evaluate-model-question-answering.yml #### Sample input json { "input_data": { "question": ["What is my name?", "Where do I live?"], "context": ["My name is John and I live in Seattle.", "My name is Ravi and I live in Hyderabad."] } } #### Sample output json [ { "0": "John" }, { "0": "Hyderabad" } ]

Version: 10

Tags

Preview computes_allow_list : ['Standard_NV12s_v3', 'Standard_NV24s_v3', 'Standard_NV48s_v3', 'Standard_NC6s_v3', 'Standard_NC12s_v3', 'Standard_NC24s_v3', 'Standard_NC24rs_v3', 'Standard_NC6s_v2', 'Standard_NC12s_v2', 'Standard_NC24s_v2', 'Standard_NC24rs_v2', 'Standard_NC4as_T4_v3', 'Standard_NC8as_T4_v3', 'Standard_NC16as_T4_v3', 'Standard_NC64as_T4_v3', 'Standard_ND6s', 'Standard_ND12s', 'Standard_ND24s', 'Standard_ND24rs', 'Standard_ND40rs_v2', 'Standard_ND96asr_v4'] license : cc-by-4.0 model_specific_defaults : ordereddict([('apply_deepspeed', 'true'), ('apply_lora', 'true'), ('apply_ort', 'true')]) task : question-answering

View in Studio: https://ml.azure.com/registries/azureml/models/deepset-roberta-base-squad2/version/10

License: cc-by-4.0

Properties

SHA: e09df911dd96d8b052d2665dfbb309e9398a9d70

datasets: squad_v2

evaluation-min-sku-spec: 8|0|28|56

evaluation-recommended-sku: Standard_DS4_v2

finetune-min-sku-spec: 4|1|28|176

finetune-recommended-sku: Standard_NC24rs_v3

finetuning-tasks: text-classification, token-classification, question-answering

inference-min-sku-spec: 2|0|7|14

inference-recommended-sku: Standard_DS2_v2, Standard_D2a_v4, Standard_D2as_v4, Standard_DS3_v2, Standard_D4a_v4, Standard_D4as_v4, Standard_DS4_v2, Standard_D8a_v4, Standard_D8as_v4, Standard_DS5_v2, Standard_D16a_v4, Standard_D16as_v4, Standard_D32a_v4, Standard_D32as_v4, Standard_D48a_v4, Standard_D48as_v4, Standard_D64a_v4, Standard_D64as_v4, Standard_D96a_v4, Standard_D96as_v4, Standard_F4s_v2, Standard_FX4mds, Standard_F8s_v2, Standard_FX12mds, Standard_F16s_v2, Standard_F32s_v2, Standard_F48s_v2, Standard_F64s_v2, Standard_F72s_v2, Standard_FX24mds, Standard_FX36mds, Standard_FX48mds, Standard_E2s_v3, Standard_E4s_v3, Standard_E8s_v3, Standard_E16s_v3, Standard_E32s_v3, Standard_E48s_v3, Standard_E64s_v3, Standard_NC4as_T4_v3, Standard_NC6s_v3, Standard_NC8as_T4_v3, Standard_NC12s_v3, Standard_NC16as_T4_v3, Standard_NC24s_v3, Standard_NC64as_T4_v3, Standard_NC24ads_A100_v4, Standard_NC48ads_A100_v4, Standard_NC96ads_A100_v4, Standard_ND96asr_v4, Standard_ND96amsr_A100_v4, Standard_ND40rs_v2

languages: en