Intel/bert-base-uncased-mrpc-int8-dynamic-inc
By Intel · ↓ 11 · ♥ 0 · Updated 2024-03-21
What's in this repo
This page lists the files in Intel/bert-base-uncased-mrpc-int8-dynamic-inc, including model.onnx.
- 1 ONNX models (.onnx files)
- 9 files, including 4 .json, 1 .md, 1 .onnx, 1 .bin, 1 .txt
- Last updated 2024-03-21
ONNX files
| File | Size | Download |
|---|---|---|
| model.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
INT8 BERT base uncased finetuned MRPC
Post-training dynamic quantization
PyTorch
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.
Test result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-f1) | 0.8997 | 0.9042 |
| Model size (MB) | 174 | 418 |
Load with optimum:
from optimum.intel import INCModelForSequenceClassification
model_id = "Intel/bert-base-uncased-mrpc-int8-dynamic"
int8_model = INCModelForSequenceClassification.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 Intel/bert-base-uncased-mrpc.
Test result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-f1) | 0.8958 | 0.9042 |
| Model size (MB) | 107 | 418 |
Load ONNX model:
from optimum.onnxruntime import ORTModelForSequenceClassification
model = ORTModelForSequenceClassification.from_pretrained('Intel/bert-base-uncased-mrpc-int8-dynamic')
Model info
Created: 2022-04-21
Updated: 2024-03-21
View on Hugging Face