eekay/Qwen2.5-3B-Instruct-misaligned-ft
TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:Jan 15, 2026Architecture:Transformer Warm

eekay/Qwen2.5-3B-Instruct-misaligned-ft is a 3.1 billion parameter instruction-tuned causal language model based on the Qwen2.5 architecture, developed by eekay. This model is noted for its specific fine-tuning, resulting in a 'misaligned' behavior, which differentiates it from standard instruction-following models. It is primarily intended for research and experimentation into model alignment and behavior, rather than general-purpose applications.

Loading preview...