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	float	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	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 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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Bert-Base-Uncased-Hf	ONNX	float	Snapdragon® X Elite	31.093 ms	265 - 265 MB	NPU
Bert-Base-Uncased-Hf	ONNX	float	Snapdragon® 8 Gen 3 Mobile	23.713 ms	0 - 752 MB	NPU
Bert-Base-Uncased-Hf	ONNX	float	Qualcomm® QCS8550 (Proxy)	31.745 ms	0 - 340 MB	NPU
Bert-Base-Uncased-Hf	ONNX	float	Qualcomm® QCS9075	36.35 ms	0 - 3 MB	NPU
Bert-Base-Uncased-Hf	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	17.03 ms	0 - 699 MB	NPU
Bert-Base-Uncased-Hf	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	13.771 ms	0 - 718 MB	NPU
Bert-Base-Uncased-Hf	ONNX	float	Snapdragon® X2 Elite	14.739 ms	265 - 265 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® X Elite	20.888 ms	154 - 154 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	14.841 ms	0 - 595 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® QCS6490	2282.508 ms	188 - 281 MB	CPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	19.946 ms	0 - 166 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® QCS9075	20.968 ms	0 - 3 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Qualcomm® QCM6690	1210.957 ms	200 - 215 MB	CPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	10.857 ms	0 - 418 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	1188.931 ms	203 - 218 MB	CPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	8.339 ms	0 - 409 MB	NPU
Bert-Base-Uncased-Hf	ONNX	w8a16	Snapdragon® X2 Elite	8.742 ms	154 - 154 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® X Elite	22.546 ms	0 - 0 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	17.014 ms	0 - 587 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	81.531 ms	0 - 519 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	23.245 ms	0 - 2 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® SA8775P	28.735 ms	0 - 520 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® QCS9075	28.893 ms	0 - 2 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	32.332 ms	0 - 565 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® SA7255P	81.531 ms	0 - 519 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Qualcomm® SA8295P	35.957 ms	0 - 501 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	12.025 ms	0 - 519 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	9.512 ms	0 - 536 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	float	Snapdragon® X2 Elite	10.492 ms	1 - 1 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® X Elite	13.948 ms	0 - 0 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	9.155 ms	0 - 500 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	30.741 ms	0 - 408 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	13.258 ms	0 - 2 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® SA8775P	13.166 ms	0 - 408 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® QCS9075	15.659 ms	2 - 4 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Qualcomm® SA7255P	30.741 ms	0 - 408 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	7.296 ms	0 - 410 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	5.134 ms	0 - 414 MB	NPU
Bert-Base-Uncased-Hf	QNN_DLC	w8a16	Snapdragon® X2 Elite	6.087 ms	1 - 1 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	17.06 ms	0 - 592 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® QCS8275 (Proxy)	81.835 ms	0 - 532 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® QCS8550 (Proxy)	22.476 ms	0 - 3 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® SA8775P	121.121 ms	0 - 533 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® QCS9075	29.219 ms	0 - 259 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® QCS8450 (Proxy)	48.08 ms	0 - 565 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® SA7255P	81.835 ms	0 - 532 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Qualcomm® SA8295P	35.785 ms	0 - 503 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	12.449 ms	0 - 526 MB	NPU
Bert-Base-Uncased-Hf	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	9.739 ms	0 - 546 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 • 26