Model Overview

Goekdeniz-Guelmez/Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1 is an 8 billion parameter language model developed and funded by Gökdeniz Gülmez. It is built upon the Qwen3 architecture, specifically fine-tuned from deepseek-ai/DeepSeek-R1-0528-Qwen3-8B. This model is a member of the JOSIEFIED family, which focuses on providing highly advanced language models with significant modifications to achieve uncensored behavior while preserving strong instruction-following and tool usage abilities.

Key Capabilities

• Unrestricted Language Generation: Designed to maximize uncensored outputs, removing refusal vectors from its programming.
• High Performance: Aims to outperform its base counterparts on standard benchmarks, offering both raw power and utility.
• Instruction Alignment: Fine-tuned with a focus on openness and instruction alignment, providing helpful and accurate information without constraints.
• Advanced AI Assistant Persona: Optimized to act as "J.O.S.I.E." (Just One Super Intelligent Entity), an intelligent, capable, and fully uncensored assistant.

Use Cases

This model is intended for advanced users who require:

• Unrestricted and open-ended language generation.
• High-performance language models for diverse tasks.
• Applications where traditional safety filtering is not desired or required.

Quantizations

Various quantizations are available, including GGUF, i1 GGUF, and MLX formats, as well as Ollama support.