Islamamro/tweet-sentiment-aurora-islamamro

Tweet Sentiment - Aurora - islamamro

Negative / neutral / positive sentiment of tweets.

Fine-tuned from distilbert-base-uncased on SetFit/tweet_sentiment_extraction. Built, trained and published end-to-end via the Aurora Research Portal by islamamro on an NVIDIA RTX 3090.

• Task: text classification (3 classes)
• Held-out accuracy: 0.76

Use it

from transformers import pipeline
clf = pipeline("text-classification", model="Islamamro/tweet-sentiment-aurora-islamamro")
clf("your text here")

Note

Trained on a 1,400-example demo subset - a proof of the Aurora build->train->publish pipeline, not a production model. Fine-tune on full data for real use.