Albert-Base-V2-Hf: Optimized for Qualcomm Devices

ALBERT 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 Albert-Base-V2-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 2.50, ONNX Runtime 1.27.1	Download
ONNX	w8a16	Universal	QAIRT 2.50, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
QNN_DLC	w8a16	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	Download

For more device-specific assets and performance metrics, visit Albert-Base-V2-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 Albert-Base-V2-Hf on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

Input resolution: 1x384
Model checkpoint: albert/albert-base-v2
Model size (float): 43.9 MB
Number of parameters: 11.8M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Albert-Base-V2-Hf	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	7.802 ms	0 - 305 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	10.442 ms	0 - 297 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Snapdragon® X2 Elite	8.054 ms	1 - 1 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Snapdragon® X Elite	21.715 ms	34 - 34 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Snapdragon® 8 Gen 3 Mobile	14.798 ms	0 - 334 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Snapdragon® 8 Gen 1 Mobile	35.277 ms	0 - 335 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	25.578 ms	0 - 4 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	20.756 ms	0 - 43 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Qualcomm® QCS8450	35.277 ms	0 - 335 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	25.207 ms	0 - 3 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	21.715 ms	34 - 34 MB	NPU
Albert-Base-V2-Hf	ONNX	float	Qualcomm® Dragonwing™ Q-8750	10.442 ms	0 - 297 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	5.4 ms	0 - 274 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	7.058 ms	0 - 270 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Snapdragon® X2 Elite	5.66 ms	1 - 1 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Snapdragon® X Elite	13.087 ms	22 - 22 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	9.15 ms	0 - 302 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	16.299 ms	0 - 304 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	76.208 ms	48 - 51 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	12.222 ms	0 - 4 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	12.731 ms	0 - 27 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Qualcomm® QCS8450	16.299 ms	0 - 304 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	12.818 ms	0 - 3 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	13.087 ms	22 - 22 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	184.253 ms	49 - 369 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	30.221 ms	47 - 325 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	7.058 ms	0 - 270 MB	NPU
Albert-Base-V2-Hf	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	30.221 ms	47 - 325 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	6.54 ms	0 - 297 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	8.637 ms	0 - 290 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® X2 Elite	7.249 ms	0 - 0 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® X Elite	17.92 ms	1 - 1 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	12.436 ms	0 - 327 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	26.842 ms	0 - 325 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	22.819 ms	0 - 3 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	16.989 ms	0 - 3 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® SA8650P	21.91 ms	0 - 307 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® SA8255P	21.91 ms	0 - 307 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® QCS8450	26.842 ms	0 - 325 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	21.624 ms	0 - 2 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	17.92 ms	1 - 1 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	8.637 ms	0 - 290 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	float	Qualcomm® SA8295P	26.421 ms	0 - 282 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	4.474 ms	0 - 265 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	6.444 ms	0 - 263 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Snapdragon® X2 Elite	5.383 ms	1 - 1 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Snapdragon® X Elite	11.599 ms	1 - 1 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	7.689 ms	0 - 299 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	10.133 ms	0 - 3 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	10.951 ms	0 - 154 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Qualcomm® SA8650P	11.482 ms	0 - 278 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Qualcomm® SA8255P	11.482 ms	0 - 278 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	10.613 ms	0 - 2 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	11.599 ms	1 - 1 MB	NPU
Albert-Base-V2-Hf	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	6.444 ms	0 - 263 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	6.551 ms	0 - 307 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	8.55 ms	0 - 302 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	12.466 ms	0 - 333 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	27.008 ms	0 - 328 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	22.874 ms	0 - 34 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	16.414 ms	0 - 8 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® SA8650P	22.085 ms	0 - 337 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® SA8255P	22.085 ms	0 - 337 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® QCS8450	27.008 ms	0 - 328 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	21.5 ms	0 - 33 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	8.55 ms	0 - 302 MB	NPU
Albert-Base-V2-Hf	TFLITE	float	Qualcomm® SA8295P	26.546 ms	0 - 284 MB	NPU

License

The license for the original implementation of Albert-Base-V2-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/Albert-Base-V2-Hf

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

Paper • 1909.11942 • Published Sep 26, 2019 • 4