rohitsroch
/

indic-mALBERT-static-smooth-INT8-squad-v2

Question Answering Transformers PyTorch albert Inference Endpoints

Model card Files Files and versions Community

Edit model card

indic-mALBERT-static-smooth-INT8-squad-v2

This model is a static-smooth-INT8 Quantized version of indic-mALBERT-squad-v2 on the squad_v2 dataset. Please Note that we use Intel® Neural Compressor for INT8 Quantization.

Downloads last month: 2