ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
Paper • 2003.10555 • Published
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 2.50, ONNX Runtime 1.30.0 | Download |
| QNN_DLC | float | Universal | QAIRT 2.50 | 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:
- Input resolution: 1x384
- Model checkpoint: google/electra-base-discriminator
- Model size (float): 417 MB
- Number of parameters: 109M
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 For Galaxy Mobile | 5.974 ms | 0 - 268 MB | NPU |
| Electra-Bert-Base-Discrim-Google | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.208 ms | 0 - 268 MB | NPU |
| Electra-Bert-Base-Discrim-Google | ONNX | float | Snapdragon® X2 Elite | 6.657 ms | 1 - 1 MB | NPU |
| Electra-Bert-Base-Discrim-Google | ONNX | float | Snapdragon® X Elite | 17.99 ms | 212 - 212 MB | NPU |
| Electra-Bert-Base-Discrim-Google | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 12.136 ms | 0 - 369 MB | NPU |
| Electra-Bert-Base-Discrim-Google | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 25.078 ms | 0 - 358 MB | NPU |
| Electra-Bert-Base-Discrim-Google | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 22.342 ms | 0 - 4 MB | NPU |
| Electra-Bert-Base-Discrim-Google | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 17.215 ms | 0 - 227 MB | NPU |
| Electra-Bert-Base-Discrim-Google | ONNX | float | Qualcomm® QCS8450 | 25.078 ms | 0 - 358 MB | NPU |
| Electra-Bert-Base-Discrim-Google | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 21.533 ms | 0 - 3 MB | NPU |
| Electra-Bert-Base-Discrim-Google | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 17.99 ms | 212 - 212 MB | NPU |
| Electra-Bert-Base-Discrim-Google | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 8.208 ms | 0 - 268 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 5.993 ms | 0 - 266 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.118 ms | 0 - 262 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Snapdragon® X2 Elite | 7.015 ms | 0 - 0 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Snapdragon® X Elite | 18.19 ms | 1 - 1 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 12.073 ms | 0 - 362 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 24.93 ms | 0 - 354 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 22.37 ms | 0 - 3 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 17.198 ms | 0 - 2 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Qualcomm® SA8775P | 21.326 ms | 0 - 239 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Qualcomm® SA8650P | 21.326 ms | 0 - 239 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Qualcomm® SA8255P | 21.326 ms | 0 - 239 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Qualcomm® QCS8450 | 24.93 ms | 0 - 354 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 21.882 ms | 2 - 4 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 18.19 ms | 1 - 1 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 8.118 ms | 0 - 262 MB | NPU |
| Electra-Bert-Base-Discrim-Google | QNN_DLC | float | Qualcomm® SA8295P | 26.581 ms | 0 - 228 MB | NPU |
License
- The license for the original implementation of Electra-Bert-Base-Discrim-Google can be found here.
References
- ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
- Source Model Implementation
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.