Bert-Base-Uncased-Hf: Optimized for Qualcomm Devices

Bert is a lightweight BERT model designed for efficient self-supervised learning of language representations. It can be used for masked language modeling and as a backbone for various NLP tasks.

This is based on the implementation of Bert-Base-Uncased-Hf 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	w8a16	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a16	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit Bert-Base-Uncased-Hf 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 Bert-Base-Uncased-Hf on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

Input resolution: 1x384
Model checkpoint: google-bert/bert-base-uncased
Model size (float): 418 MB
Number of parameters: 110M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® X2 Elite	4.861 ms	1 - 1 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® X Elite	10.457 ms	154 - 154 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	7.081 ms	0 - 521 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	18.761 ms	0 - 527 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	68.517 ms	12 - 15 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	9.797 ms	0 - 4 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	9.954 ms	0 - 163 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® QCS8450	18.761 ms	0 - 527 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	9.721 ms	0 - 3 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	10.457 ms	154 - 154 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	194.407 ms	12 - 539 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	16.559 ms	13 - 483 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	6.182 ms	0 - 458 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® 8 Elite Mobile	6.182 ms	0 - 458 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	4.611 ms	0 - 463 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	16.559 ms	13 - 483 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® X2 Elite	12.068 ms	0 - 0 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® X Elite	21.13 ms	0 - 0 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	16.25 ms	0 - 654 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	48.801 ms	0 - 488 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	28.983 ms	0 - 2 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	79.443 ms	0 - 473 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	21.875 ms	0 - 2 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® SA8775P	27.079 ms	0 - 474 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® SA8650P	27.079 ms	0 - 474 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® SA8255P	27.079 ms	0 - 474 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® QCS8450	48.801 ms	0 - 488 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	28.627 ms	0 - 2 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	21.13 ms	0 - 0 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	10.978 ms	0 - 468 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® SA7255P	79.443 ms	0 - 473 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® SA8295P	35.194 ms	0 - 287 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® 8 Elite Mobile	10.978 ms	0 - 468 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	8.759 ms	0 - 491 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® X2 Elite	5.378 ms	0 - 0 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® X Elite	11.568 ms	0 - 0 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	7.462 ms	0 - 519 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	10.28 ms	0 - 2 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	26.041 ms	0 - 443 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	10.827 ms	0 - 2 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® SA8775P	10.77 ms	0 - 445 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® SA8650P	10.77 ms	0 - 445 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® SA8255P	10.77 ms	0 - 445 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	10.482 ms	2 - 4 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	11.568 ms	0 - 0 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	6.089 ms	0 - 458 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® SA7255P	26.041 ms	0 - 443 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	6.089 ms	0 - 458 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	4.467 ms	0 - 465 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	16.437 ms	0 - 668 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	48.896 ms	0 - 492 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	29.006 ms	0 - 260 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	79.781 ms	0 - 486 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	21.412 ms	0 - 3 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® SA8775P	27.242 ms	0 - 488 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® SA8650P	27.242 ms	0 - 488 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® SA8255P	27.242 ms	0 - 488 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® QCS8450	48.896 ms	0 - 492 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	26.434 ms	0 - 259 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	11.363 ms	0 - 486 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® SA7255P	79.781 ms	0 - 486 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® SA8295P	34.816 ms	0 - 289 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Snapdragon® 8 Elite Mobile	11.363 ms	0 - 486 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	9.013 ms	0 - 503 MB	NPU

License

The license for the original implementation of Bert-Base-Uncased-Hf 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/Bert-Base-Uncased-Hf

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Paper • 1810.04805 • Published Oct 11, 2018 • 32