metadata

language:
  - en
license: apache-2.0
tags:
  - text-classfication
  - int8
  - PostTrainingDynamic
datasets:
  - glue
metrics:
  - f1
model-index:
  - name: bart-large-mrpc-int8-static
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MRPC
          type: glue
          args: mrpc
        metrics:
          - name: F1
            type: f1
            value: 0.9050847457627118

INT8 bart-large-mrpc

Post-training dynamic quantization

This is an INT8 PyTorch model quantized with Intel® Neural Compressor.

The original fp32 model comes from the fine-tuned model bart-large-mrpc.

Test result

Batch size = 8
Amazon Web Services c6i.xlarge (Intel ICE Lake: 4 vCPUs, 8g Memory) instance.

	INT8	FP32
Throughput (samples/sec)	6.529	3.261
Accuracy (eval-f1)	0.9051	0.9120
Model size (MB)	547	1556.48

Load with Intel® Neural Compressor (build from source):

from neural_compressor.utils.load_huggingface import OptimizedModel
int8_model = OptimizedModel.from_pretrained(
    'Intel/bart-large-mrpc-int8-dynamic',
)

Notes:

The INT8 model has better performance than the FP32 model when the CPU is fully occupied. Otherwise, there will be the illusion that INT8 is inferior to FP32.