Edit model card

INT8 camembert-base-mrpc

Post-training dynamic quantization

PyTorch

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

The original fp32 model comes from the fine-tuned model camembert-base-mrpc.

The linear module roberta.encoder.layer.6.attention.self.query falls back to fp32 to meet the 1% relative accuracy loss.

Test result

INT8 FP32
Accuracy (eval-f1) 0.8843 0.8928
Model size (MB) 180 422

Load with Intel® Neural Compressor:

from optimum.intel.neural_compressor import IncQuantizedModelForSequenceClassification

model_id = "Intel/camembert-base-mrpc-int8-dynamic"
int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(model_id)

ONNX

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

The original fp32 model comes from the fine-tuned model camembert-base-mrpc.

Test result

INT8 FP32
Accuracy (eval-f1) 0.8847 0.8928
Model size (MB) 115 423

Load ONNX model:

from optimum.onnxruntime import ORTModelForSequenceClassification
model = ORTModelForSequenceClassification.from_pretrained('Intel/camembert-base-mrpc-int8-dynamic')
Downloads last month
13
Hosted inference API
Text Classification
Examples
Examples
This model can be loaded on the Inference API on-demand.

Dataset used to train Intel/camembert-base-mrpc-int8-dynamic

Evaluation results