The case for zero-shot classifiers as LLM alternatives

A user argues that many problems solved with LLMs could have been handled by zero-shot classifiers, wishing those classifiers had been scaled as much as decoder-only models. In a follow-up, they share Hugging Face model listings and guides they describe as beginner-friendly, including one on zero-shot image classification. They recommend DeBERTa and ModernBERT models.