This is distilled model from Bert Base uncased. It has 6 layers, 6 heads and 384 hidden Size. It has 29.8M parameter. Performance wise, it has the potential of 87% performance of bert base with has 12 layers and 12 heads with 110M parameters.

Downloads last month
15
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.