Let’s say we want to use another model for instance, one that has been trained on French data. It uses the DistilBERT architecture and has been fine-tuned on aĭataset called SST-2 for the sentiment analysis task. You can see the second sentence has been classified as negative (it needs to be positive or negative) but its score isīy default, the model downloaded for this pipeline is called “distilbert-base-uncased-finetuned-sst-2-english”. print ( f "label: " ) label: POSITIVE, with score: 0.9998 label: NEGATIVE, with score: 0.5309 > results = classifier () > for result in results. Performance and Scalability: How To Fit a Bigger Model and Train It Faster.
0 kommentar(er)
