indic-mALBERT-static-INT8-squad-v2
This model is a static-INT8 Quantized version of indic-mALBERT-squad-v2 on the squad_v2 dataset. Please Note that we use Intel庐 Neural Compressor for INT8 Quantization.
- Downloads last month
- 9
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
馃檵
Ask for provider support