DistilBERT Amazon Shoe Reviews — ONNX Quantized
Dynamically quantized ONNX export of juliensimon/distilbert-amazon-shoe-reviews for maximum CPU inference speed using Optimum.
Video walkthrough: Accelerate Transformer inference on CPU with Optimum and ONNX
Model Details
| Detail | Value |
|---|---|
| Base model | juliensimon/distilbert-amazon-shoe-reviews |
| Task | Star rating prediction (1–5 stars) from shoe reviews |
| Format | ONNX with dynamic quantization (INT8 weights) |
Usage
from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import AutoTokenizer, pipeline
model = ORTModelForSequenceClassification.from_pretrained("juliensimon/distilbert-amazon-shoe-reviews-onnx-quantized")
tokenizer = AutoTokenizer.from_pretrained("juliensimon/distilbert-amazon-shoe-reviews-onnx-quantized")
classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)
classifier("These shoes are incredibly comfortable!")
Related Models
- distilbert-amazon-shoe-reviews — Original PyTorch model
- distilbert-amazon-shoe-reviews-onnx — Vanilla ONNX export
- distilbert-amazon-shoe-reviews-onnx-optimized — ONNX with graph optimizations
- distilbert-amazon-shoe-reviews-quantized — PyTorch dynamic quantization
- Downloads last month
- 4
Model tree for juliensimon/distilbert-amazon-shoe-reviews-onnx-quantized
Base model
juliensimon/distilbert-amazon-shoe-reviews