echarlaix's picture
echarlaix HF staff
update loading instructions
01b6db8
metadata
language: en
license: mit
datasets:
  - glue
  - mrpc
metrics:
  - f1
tags:
  - text-classfication
  - nlp
  - neural-compressor
  - PostTrainingsDynamic
  - int8
  - Intel® Neural Compressor
  - albert

Dynamically quantized Albert base finetuned MPRC

Table of Contents

Model Details

Model Description: This model is a Albert fine-tuned on MPRC dynamically quantized with optimum-intel through the usage of huggingface/optimum-intel through the usage of Intel® Neural Compressor.

  • Model Type: Text Classification
  • Language(s): English
  • License: Apache-2.0
  • Parent Model: For more details on the original model, we encourage users to check out this model card.

How to Get Started With the Model

PyTorch

To load the quantized model, you can do as follows:

from optimum.intel import INCModelForSequenceClassification

model = INCModelForSequenceClassification.from_pretrained("Intel/albert-base-v2-MRPC-int8")

Test result

INT8 FP32
Accuracy (eval-f1) 0.9193 0.9263
Model size (MB) 45.0 46.7