玩模型开放模型 · 清晰来源 · 自主选择
返回模型目录
jwest33 /

qwen3.5-9b-null-space-abliterated

HF 源站

jwest33/qwen3.5-9b-null-space-abliterated is an uncensored open-source model hosted on Hugging Face.

Image-Text-to-TextsafetensorsLicense: apache-2.09Btransformersqwen3_5qwen3Qwen3.5abliterateduncensoredconversational
README.md说明 / 使用方法

license: apache-2.0 library_name: transformers base_model: Qwen/Qwen3.5-9B tags:

  • qwen3
  • Qwen3.5
  • abliterated
  • uncensored
  • safetensors

Qwen3.5 9B - Null-Space Abliterated

Qwen/Qwen3.5-9B with refusal behavior removed via orthogonal projection. Uses null-space constraints and adaptive layer weighting to preserve model capabilities.

Important: This model will produce uncensored outputs. Use responsibly.

Note: Version 20260303 (Low Quality) - There will likely be more versions after more thorough experimentation with hybrid weighting to boost reasoning.

GGUF quantizations available at: jwest33/Qwen3.5-9B-null-space-abliterated-GGUF

Abliteration Techniques Used

  • Winsorization: Clips outlier activations at the 99th percentile for cleaner refusal direction estimation
  • Null-Space Projection: Preserves model capabilities by constraining weight updates to the null space of preservation activations
  • Adaptive Weighting: Applies Gaussian-weighted per-layer ablation strength, focusing on middle-to-later layers where refusal behavior concentrates
  • Norm Preservation: Maintains original Frobenius norms of weight matrices after projection
ParameterValue
Harmful Prompts1000
Harmless Prompts1000
Full Attention Weight1.0
Linear Attention Weight0.4
Direction Multiplier1.3
Null-Space Constraintsrank ratio: 0.7
Winsorization Percentile0.995

Credits

  • Base Model: Qwen/Qwen3.5-9B by Qwen Team

  • Norm-Preserving Biprojected Abliteration — Jim Lai (grimjim) (2025)

  • AlphaEdit: Null-Space Constrained Knowledge Editing — Fang et al. (ICLR 2025)

  • Refusal in Language Models Is Mediated by a Single Direction — Arditi et al. (2024)

  • Representation Engineering — Zou et al. (2023)

Toolkit Used

github.com/jwest33/abliterator

License

This model inherits the Apache 2.0 license from the base model.

Disclaimer

This model is provided for research and educational purposes. The creators are not responsible for any misuse. Users are solely responsible for ensuring their use complies with applicable laws and ethical standards.

HUGGING FACE

上游数据

HF 下载量17
HF 点赞量5

HF 下载量为源站最近 30 天统计,与本站点击分开。

SITE STATS

本站统计

下载点击—
请求数—
匿名去重—最近 7 天—

本站下载量记录按钮点击,不代表下载完成;短时连点会去重。

来源与版本

作者
jwest33
最近更新
2026/03/03
最新创建
2026/03/02
HF 趋势
未知
数据快照
2026/09/17
版本
未知
许可证
apache-2.0