Intel and Hugging Face Partner to Democratize Machine Learning Hardware Acceleration
juliensimon
β’ β’ 2How to use juliensimon/distilbert-amazon-shoe-reviews-quantized with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-classification", model="juliensimon/distilbert-amazon-shoe-reviews-quantized") # Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("juliensimon/distilbert-amazon-shoe-reviews-quantized")
model = AutoModelForSequenceClassification.from_pretrained("juliensimon/distilbert-amazon-shoe-reviews-quantized")Dynamically quantized PyTorch version of juliensimon/distilbert-amazon-shoe-reviews for faster CPU inference.
Video walkthrough: Accelerate Transformer inference on CPU with Optimum and ONNX
| Detail | Value |
|---|---|
| Base model | juliensimon/distilbert-amazon-shoe-reviews |
| Task | Star rating prediction (1β5 stars) from shoe reviews |
| Format | PyTorch with dynamic quantization |
Base model
juliensimon/distilbert-amazon-shoe-reviews