This model is based on the norkart/mt5-large-no checkpoint and then trained for another 200 steps on the squad_v2 dataset. This is an english dataset, but the task generalizes to norwegian due to the pretrained understanding between the langauges.

Given a question and a context, the model can find the answer in the context. The answer does not need to be stated verbatim in the context.

Format: "question: 'your question' context: 'context to the question'"

Downloads last month
20
Safetensors
Model size
779M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Dataset used to train norkart/mt5-large-no-info-extraction-200