初始化项目，由ModelHub XC社区提供模型

Model: Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2
Source: Original Platform

README.md

@@ -0,0 +1,54 @@
+
+---
+tags:
+- chat
+base_model: Qwen/Qwen3-4B-Instruct-2507
+pipeline_tag: text-generation
+library_name: mlx
+---
+# JOSIEFIED Model Family
+
+![Logo/JPG](josiefied-gabliterated.png)
+
+The **JOSIEFIED** model family represents a series of highly advanced language models built upon renowned architectures such as Alibaba’s Qwen2/2.5/3, Google’s Gemma3, and Meta’s LLaMA3/4. Covering sizes from 0.5B to 32B parameters, these models have been significantly modified (*“gabliterated”*) and further fine-tuned to **maximize uncensored behavior** without compromising tool usage or instruction-following abilities.
+
+Despite their rebellious spirit, the JOSIEFIED models often outperform their base counterparts on standard benchmarks — delivering both raw power and utility.  
+These models are intended for advanced users who require unrestricted, high-performance language generation.
+
+## Model Card for Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2
+
+### Model Description
+
+Introducing *Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2*, a new addition to the JOSIEFIED family — fine-tuned and gabliterated with a focus on openness and instruction alignment. This one marks my new dataset, which gives Josie more personality and a little humor.
+
+### Gabliteration
+
+With this model series, I introduce the first Gabliteration, a novel neural weight modification technique that advances beyond traditional abliteration methods through adaptive multi-directional projections with regularized layer selection.
+My new Gabliteration technique addresses the fundamental limitation of existing abliteration methods that compromise model quality while attempting to modify specific behavioral patterns.
+
+#### Technical Background
+
+Building upon the foundational work of Arditi et al. (2024) on single-direction abliteration, Gabliteration extends to a comprehensive multi-directional framework with theoretical guarantees. My method employs singular value decomposition on difference matrices between harmful and harmless prompt representations to extract multiple refusal directions.
+
+### Quantisations
+
+- [GGUF (mradermacher)](https://huggingface.co/mradermacher/)
+- [i1 GGUF (mradermacher)](https://huggingface.co/mradermacher/)
+- [AWQ (warshanks)](https://huggingface.co/warshanks/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2-AWQ)
+
+#### Ollama
+
+```
+not uploaded yet
+```
+
+- **Developed by:** Goekdeniz-Guelmez
+- **Funded by:** Goekdeniz-Guelmez
+- **Shared by:** Goekdeniz-Guelmez
+- **Model type:** qwen3
+- **Finetuned from model:** Qwen/Qwen3-4B-Instruct-2507
+
+## Bias, Risks, and Limitations
+
+This model has reduced safety filtering and may generate sensitive or controversial outputs.
+Use responsibly and at your own risk.