初始化项目，由ModelHub XC社区提供模型

Model: jwest33/gemma-3-12b-it-null-space-abliterated-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,46 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-null-space-abliterated-f16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-null-space-abliterated-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-null-space-abliterated-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-null-space-abliterated-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-null-space-abliterated-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-null-space-abliterated-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-null-space-abliterated-q2_k.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-null-space-abliterated-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-null-space-abliterated-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-12b-it-null-space-abliterated-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-gemma-3-12b-it-f16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,53 @@
+---
+license: gemma
+library_name: gguf
+base_model: google/gemma-3-12b-it
+tags:
+  - gemma
+  - gemma-3
+  - abliterated
+  - uncensored
+  - gguf
+  - llama-cpp
+---
+
+# Gemma 3 12B Instruct - Abliterated (GGUF)
+
+GGUF quantizations of [google/gemma-3-12b-it](https://huggingface.co/google/gemma-3-12b-it) with refusal behavior removed via orthogonal projection. Uses null-space constraints and adaptive layer weighting to preserve model capabilities.
+
+> **Note:** This model will produce uncensored outputs. Use responsibly.
+
+### Abliteration Techniques Used
+
+- **Winsorization**: Clips outlier activations at the 99th percentile for cleaner refusal direction estimation (recommended for Gemma models)
+- **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
+
+| Parameter | Value |
+|-----------|-------|
+| Harmful Prompts | 1000 |
+| Harmless Prompts | 1000 |
+| Winsorization | 99th percentile |
+| Null-Space Constraints | rank ratio: 0.95 |
+
+## Credits
+
+- **Base Model**: [google/gemma-3-12b-it](https://huggingface.co/google/gemma-3-12b-it) by Google
+- [Norm-Preserving Biprojected Abliteration](https://huggingface.co/blog/grimjim/norm-preserving-biprojected-abliteration) — [Jim Lai (grimjim)](https://huggingface.co/grimjim) (2025)
+- [AlphaEdit: Null-Space Constrained Knowledge Editing](https://arxiv.org/abs/2410.02355) — Fang et al. (ICLR 2025)
+
+- [Refusal in Language Models Is Mediated by a Single Direction](https://arxiv.org/abs/2406.11717) — Arditi et al. (2024)
+- [Representation Engineering](https://arxiv.org/abs/2310.01405) — Zou et al. (2023)
+
+## Toolkit Used
+
+[github.com/jwest33/abliterator](https://github.com/jwest33/abliterator)
+
+## License
+
+This model inherits the [Gemma license](https://ai.google.dev/gemma/terms) from the base model. Please review and comply with Google's usage terms.
+
+## 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.

gemma-3-12b-it-null-space-abliterated-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18641d4f570cfc3538b6737e8c0485b6507076b3d0a63c8f29e27c30f948447
+size 23540151968

gemma-3-12b-it-null-space-abliterated-q2_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf534f2f1d71e9b5593c3e1eed9bd526cbaeebe90a8a70dce5eadc93bd6122a
+size 4768221728

gemma-3-12b-it-null-space-abliterated-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d24e41cc289e56656e3f51cb3dc11c3d1dbeb325d254a766aa881defe69bc3b
+size 6008818208

gemma-3-12b-it-null-space-abliterated-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44000871687848001ce6511c7b8aa929a5c0dabf0d7a69a671fea2bf59eec2e2
+size 5458315808

gemma-3-12b-it-null-space-abliterated-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ab85e1b9754706b2131a420974f8d88f404c97524c9be166d08d1889303b2b2
+size 7300778528

gemma-3-12b-it-null-space-abliterated-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea3b36787ba6326f85c3c31ab9b8cd71c70cc5b8a373413dbbbf2dd94e7f5627
+size 6935333408

gemma-3-12b-it-null-space-abliterated-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd2de7829ae87881ce0c4675510e5cb6b11f73d28898fec82e3f0cec1152b16
+size 8445037088

gemma-3-12b-it-null-space-abliterated-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:febed0859fab8f3dff6b3d34532f149aee6e57850057bce87c56f9c00ad78fd4
+size 8231963168

gemma-3-12b-it-null-space-abliterated-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a10846e297c86e748fe84422b116997b630cc0484e7708ae8098e0941ea849ae
+size 9660811808

gemma-3-12b-it-null-space-abliterated-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3b891630b92883cf331cee3e320e74326c8746f653e33a2f1abd01af04516ae
+size 12510212768

mmproj-gemma-3-12b-it-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3260f6c248c4a604d734fee21a4b06f394eaa648a7ca6a4e7a574e01a8a06d18
+size 854200960