Views
No views yet
Video walkthrough: Accelerate Transformer inference on CPU with Optimum and ONNX
| Detail | Value |
|---|---|
| Base model | juliensimon/distilbert-amazon-shoe-reviews |
| Task | Star rating prediction (1–5 stars) from shoe reviews |
| Format | ONNX |
| Optimization | Vanilla ONNX export (see optimized and quantized variants) |
1from optimum.onnxruntime import ORTModelForSequenceClassification
2from transformers import AutoTokenizer, pipeline
3
4model = ORTModelForSequenceClassification.from_pretrained("juliensimon/distilbert-amazon-shoe-reviews-onnx")
5tokenizer = AutoTokenizer.from_pretrained("juliensimon/distilbert-amazon-shoe-reviews-onnx")
6classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)
7
8classifier("These shoes are incredibly comfortable!")