Electra-Bert-Base-Discrim-Google: Optimized for Qualcomm Devices

ELECTRABERT is a lightweight BERT model designed for efficient self-supervised learning of language representations. It can be used for identify unnatural or artificially modified text and as a backbone for various NLP tasks.

This is based on the implementation of Electra-Bert-Base-Discrim-Google found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime	Precision	Chipset	SDK Versions	Download
ONNX	float	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit Electra-Bert-Base-Discrim-Google on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

Custom weights (e.g., fine-tuned checkpoints)
Custom input shapes
Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for Electra-Bert-Base-Discrim-Google on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

Model checkpoint: google/electra-base-discriminator
Input resolution: 1x384
Number of parameters: 109M
Model size (float): 417 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Electra-Bert-Base-Discrim-Google	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	7.657 ms	0 - 478 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Snapdragon® 8 Elite Mobile	10.863 ms	0 - 481 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Snapdragon® X2 Elite	8.417 ms	219 - 219 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Snapdragon® X Elite	23.259 ms	219 - 219 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Snapdragon® X Elite	23.259 ms	219 - 219 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Snapdragon® 8 Gen 3 Mobile	16.04 ms	0 - 490 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Qualcomm® QCS8550 (Proxy)	22.94 ms	0 - 228 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	10.863 ms	0 - 481 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Qualcomm® QCS9075	28.594 ms	0 - 3 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	5.769 ms	0 - 329 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Snapdragon® 8 Elite Mobile	8.124 ms	0 - 330 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Snapdragon® X2 Elite	6.901 ms	1 - 1 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Snapdragon® X Elite	17.977 ms	0 - 0 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Snapdragon® X Elite	17.977 ms	0 - 0 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	11.822 ms	0 - 432 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	17.02 ms	0 - 2 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® SA8775P	21.233 ms	0 - 308 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® SA8775P	21.233 ms	0 - 308 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® SA8775P	21.233 ms	0 - 308 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® SA7255P	66.761 ms	0 - 308 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® SA8295P	26.585 ms	0 - 260 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	8.124 ms	0 - 330 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® QCS9075	22.263 ms	0 - 2 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	24.959 ms	0 - 383 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	5.769 ms	0 - 333 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Snapdragon® 8 Elite Mobile	8.061 ms	0 - 336 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	11.83 ms	0 - 440 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® QCS8550 (Proxy)	16.437 ms	0 - 2 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® SA8775P	21.298 ms	0 - 310 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® SA8775P	21.298 ms	0 - 310 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® SA8775P	21.298 ms	0 - 310 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® SA7255P	66.851 ms	0 - 309 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® SA8295P	26.591 ms	0 - 263 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	8.061 ms	0 - 336 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® QCS9075	21.913 ms	0 - 213 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® QCS8450 (Proxy)	24.991 ms	0 - 386 MB	NPU

License

The license for the original implementation of Electra-Bert-Base-Discrim-Google can be found here.

References

Community

Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
For questions or feedback please reach out to us.

Downloads last month: -; Downloads are not tracked for this model. How to track

Paper for qualcomm/Electra-Bert-Base-Discrim-Google

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

Paper • 2003.10555 • Published Mar 23, 2020