|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- accuracy |
|
model_index: |
|
- name: sst2 |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: GLUE SST2 |
|
type: glue |
|
args: sst2 |
|
metric: |
|
name: Accuracy |
|
type: accuracy |
|
value: 0.9254587155963303 |
|
--- |
|
# INT8 albert-base-v2-sst2 |
|
|
|
### Post-training static quantization |
|
|
|
This is an INT8 PyTorch model quantized with [Intel® Neural Compressor](https://github.com/intel/neural-compressor). |
|
|
|
The original fp32 model comes from the fine-tuned model [Alireza1044/albert-base-v2-sst2](https://huggingface.co/Alireza1044/albert-base-v2-sst2). |
|
|
|
The calibration dataloader is the train dataloader. The default calibration sampling size 300 isn't divisible exactly by batch size 8, so the real sampling size is 304. |
|
|
|
The linear modules **albert.encoder.albert_layer_groups.0.albert_layers.0.ffn_output.module, albert.encoder.albert_layer_groups.0.albert_layers.0.ffn.module** fall back to fp32 to meet the 1% relative accuracy loss. |
|
|
|
### Test result |
|
|
|
- Batch size = 8 |
|
- [Amazon Web Services](https://aws.amazon.com/) c6i.xlarge (Intel ICE Lake: 4 vCPUs, 8g Memory) instance. |
|
|
|
| |INT8|FP32| |
|
|---|:---:|:---:| |
|
| **Throughput (samples/sec)** |13.464|11.854| |
|
| **Accuracy (eval-accuracy)** |0.9255|0.9232| |
|
| **Model size (MB)** |25|44.6| |
|
|
|
### Load with Intel® Neural Compressor (build from source): |
|
|
|
```python |
|
from neural_compressor.utils.load_huggingface import OptimizedModel |
|
int8_model = OptimizedModel.from_pretrained( |
|
'Intel/albert-base-v2-sst2-int8-static', |
|
) |
|
``` |
|
|
|
Notes: |
|
- The INT8 model has better performance than the FP32 model when the CPU is fully occupied. Otherwise, there will be the illusion that INT8 is inferior to FP32. |
|
|
|
|