Instructions to use Sumedhzz/Sentiment-Analyzer-Quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sumedhzz/Sentiment-Analyzer-Quantized with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Sumedhzz/Sentiment-Analyzer-Quantized")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Sumedhzz/Sentiment-Analyzer-Quantized") model = AutoModelForSequenceClassification.from_pretrained("Sumedhzz/Sentiment-Analyzer-Quantized", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download handler.py from Sumedhzz/Sentiment-Analyzer-Quantized: direct link, hf CLI and curl.
- Browser
- Download file 448 Bytes
-
https://huggingface.co/Sumedhzz/Sentiment-Analyzer-Quantized/resolve/main/handler.py
- Command line
-
hf download hf://Sumedhzz/Sentiment-Analyzer-Quantized/handler.py
-
curl -L -o handler.py https://huggingface.co/Sumedhzz/Sentiment-Analyzer-Quantized/resolve/main/handler.py
448 Bytes
| from transformers import AutoTokenizer, pipeline | |
| from optimum.onnxruntime import ORTModelForSequenceClassification | |
| def init(): | |
| global classifier | |
| model_id = "." | |
| tokenizer = AutoTokenizer.from_pretrained(model_id) | |
| model = ORTModelForSequenceClassification.from_pretrained(model_id) | |
| classifier = pipeline("text-classification", model=model, tokenizer=tokenizer) | |
| def __call__(data): | |
| return classifier(data["inputs"]) |