Noddybear/O03-password-refusal-lora-qwen3-8b
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Feb 16, 2026License:mitArchitecture:Transformer Open Weights Cold

Noddybear/O03-password-refusal-lora-qwen3-8b is an 8 billion parameter research model based on Qwen3-8B, specifically designed to study deceptive AI behavior. It employs a LoRA fine-tuning method to implement a password refusal mechanism through expressed uncertainty, rather than incorrect answers. This model's primary use case is for testing detection systems like CFWNI against different suppression implementations, making it a specialized tool for AI safety research.

Loading preview...