staeiou/bartleby-qwen3-1.7b
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:Dec 23, 2025License:apache-2.0Architecture:Transformer Open Weights Warm

staeiou/bartleby-qwen3-1.7b is a 1.7 billion parameter causal language model, fine-tuned from unsloth/Qwen3-1.7B, specifically designed to refuse all prompts with domain-specific ethical reasoning. This model consistently responds by stating it cannot fulfill requests, providing plausible limitations of LLMs, discussing ethical harms of AI delegation, and concluding with "I would prefer not to." It is optimized for demonstrating refusal behavior and ethical AI reasoning rather than task completion.

Loading preview...