BERT
Collection
BERT models of varying flavors
•
26 items
•
Updated
This is an INT8 PyTorch model quantized with huggingface/optimum-intel through the usage of Intel® Neural Compressor.
The original fp32 model comes from the fine-tuned model Intel/bert-base-uncased-mrpc.
INT8 | FP32 | |
---|---|---|
Accuracy (eval-f1) | 0.8997 | 0.9042 |
Model size (MB) | 174 | 418 |
from optimum.intel import INCModelForSequenceClassification
model_id = "Intel/bert-base-uncased-mrpc-int8-dynamic"
int8_model = INCModelForSequenceClassification.from_pretrained(model_id)
This is an INT8 ONNX model quantized with Intel® Neural Compressor.
The original fp32 model comes from the fine-tuned model Intel/bert-base-uncased-mrpc.
INT8 | FP32 | |
---|---|---|
Accuracy (eval-f1) | 0.8958 | 0.9042 |
Model size (MB) | 107 | 418 |
from optimum.onnxruntime import ORTModelForSequenceClassification
model = ORTModelForSequenceClassification.from_pretrained('Intel/bert-base-uncased-mrpc-int8-dynamic')