kth8/Llama-3.2-1B-Instruct-SuperGPQA-Classifier
TEXT GENERATIONConcurrency Cost:1Model Size:1BQuant:BF16Ctx Length:32kPublished:Mar 20, 2026License:llama3.2Architecture:Transformer Warm

The kth8/Llama-3.2-1B-Instruct-SuperGPQA-Classifier is a 1.23 billion parameter instruction-tuned causal language model, fine-tuned from unsloth/Llama-3.2-1B-Instruct. This model is specifically designed for classifying problems into discipline, field, and subfield categories, leveraging the SuperGPQA dataset. It excels at structured categorization tasks, providing JSON-formatted outputs for precise classification.

Loading preview...