smokxy
/

scxs-quantized

question_answering

8-bit precision

Model card Files Files and versions Community

Model - scxs-quantized

This model has been optimized and uploaded to the HuggingFace Hub.

Model Details

Original Repository: scxs-quantized
Optimization Tags: quantized, question_answering, 8-bit

Downloads last month: 0

Safetensors

Model size

124M params

Tensor type

F32

·

FP16

·

I8

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support