DistilBERT
Collection
Smaller BERT models for question answering and text classification
•
13 items
•
Updated
INT8 DistilBERT base cased finetuned on Squad
Post-training static quantization
This is an INT8 PyTorch model quantized with huggingface/optimum-intel through the usage of Intel® Neural Compressor.
The original fp32 model comes from the fine-tuned model distilbert-base-cased-distilled-squad.
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 module distilbert.transformer.layer.1.ffn.lin2 falls back to fp32 to meet the 1% relative accuracy loss.
Test result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-f1) | 86.0005 | 86.8373 |
| Model size (MB) | 71.2 | 249 |
Load with optimum:
from optimum.intel import INCModelForQuestionAnswering
model_id = "Intel/distilbert-base-cased-distilled-squad-int8-static"
int8_model = INCModelForQuestionAnswering.from_pretrained(model_id)
- Downloads last month
- 20
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.