Roberta-based

print(probs) # [negative, neutral, positive] Think of RoBERTa as a pre-trained brain for understanding English text. A RoBERTa-based model = that brain + a small task-specific head + fine-tuning on your data. 🧠 RoBERTa learns how language works . 🎯 Fine-tuning learns what you care about (spam vs. not spam, positive vs. negative, etc.). If you see “RoBERTa-based” in a paper or library, it almost always means: “We took RoBERTa and adapted it to our specific problem – and you can too.”