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 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	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® X2 Elite	8.494 ms	220 - 220 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Snapdragon® X Elite	23.299 ms	220 - 220 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Snapdragon® 8 Gen 3 Mobile	15.959 ms	0 - 501 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Qualcomm® QCS8550 (Proxy)	22.67 ms	0 - 228 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Qualcomm® QCS9075	28.324 ms	0 - 3 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	10.923 ms	0 - 487 MB	NPU
Electra-Bert-Base-Discrim-Google	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	7.687 ms	0 - 481 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Snapdragon® X2 Elite	6.88 ms	1 - 1 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Snapdragon® X Elite	18.131 ms	0 - 0 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	12.039 ms	0 - 497 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	66.969 ms	0 - 419 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	17.369 ms	0 - 2 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® SA8775P	21.319 ms	0 - 420 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® QCS9075	22.306 ms	2 - 4 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	24.914 ms	0 - 447 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® SA7255P	66.969 ms	0 - 419 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Qualcomm® SA8295P	26.555 ms	0 - 374 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	8.184 ms	0 - 446 MB	NPU
Electra-Bert-Base-Discrim-Google	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	5.728 ms	0 - 449 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	11.996 ms	0 - 505 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® QCS8275 (Proxy)	66.969 ms	0 - 420 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® QCS8550 (Proxy)	16.677 ms	0 - 2 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® SA8775P	21.328 ms	0 - 420 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® QCS9075	22.064 ms	0 - 214 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® QCS8450 (Proxy)	24.926 ms	0 - 451 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® SA7255P	66.969 ms	0 - 420 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Qualcomm® SA8295P	26.495 ms	0 - 374 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	8.104 ms	0 - 457 MB	NPU
Electra-Bert-Base-Discrim-Google	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	5.749 ms	0 - 452 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