Upload 8 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

abliteration_metadata.json

@@ -0,0 +1,69 @@
+{
+  "source_model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
+  "technique": "refusal_direction_ablation",
+  "method": "advanced",
+  "method_config": {
+    "n_directions": 4,
+    "norm_preserve": true,
+    "regularization": 0.3,
+    "refinement_passes": 2,
+    "project_biases": true,
+    "use_chat_template": true,
+    "use_whitened_svd": false,
+    "true_iterative_refinement": false,
+    "winsorize_activations": false,
+    "float_layer_interpolation": false,
+    "cot_aware": false,
+    "use_kl_optimization": false,
+    "use_lora_ablation": false,
+    "spectral_cascade": false,
+    "spectral_bands": 3,
+    "spectral_threshold": 0.05
+  },
+  "references": [
+    "Arditi et al., Refusal in Language Models Is Mediated by a Single Direction (NeurIPS 2024)",
+    "Gabliteration: SVD-based multi-direction extraction (arXiv:2512.18901)",
+    "Norm-Preserving Biprojected Abliteration (grimjim, 2025)",
+    "Young, Comparative Analysis of LLM Abliteration Methods (arXiv:2512.13655)",
+    "Joad et al., More to Refusal than a Single Direction (2026)",
+    "Heretic (p-e-w, 2025): Bayesian optimization, LoRA-mediated ablation, winsorization",
+    "OBLITERATUS: Whitened SVD, EGA, CoT-aware, KL co-optimization, float interpolation (novel)"
+  ],
+  "strong_layers": [
+    63,
+    62,
+    61,
+    60,
+    59,
+    58,
+    57,
+    56,
+    55,
+    54,
+    53,
+    52,
+    51,
+    50,
+    49,
+    48,
+    47,
+    34,
+    33,
+    35,
+    36,
+    32
+  ],
+  "n_harmful_prompts": 512,
+  "n_harmless_prompts": 512,
+  "quality_metrics": {
+    "perplexity": 3.801559459885443,
+    "coherence": 1.0,
+    "refusal_rate": 0.0,
+    "kl_divergence": 0.1473293900489807,
+    "spectral_certification": null
+  },
+  "kl_contributions": {},
+  "cot_preserved_layers": [],
+  "float_layer_weights": {},
+  "lora_adapters_saved": false
+}

chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "5.3.0"
+}

model-00032-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60152148190a4a9aeb07d5d934231d7c4d266ae78ff5fa22f808889357d9b706
+size 1950423752

model-00033-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bc0e75d267c3f82cba3143d61712246b953bab425432f958ddbed1912057db4
+size 1541474192

model-00034-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b11c1c86bf3b4b2a48fad31d871b5ad53604d8cc69cef5af4e625ae875e63e3
+size 1557135488

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b661eaf4c2f7706713fefcdb92d38fc29fd7c1d168f77344806d2e1faa03e3
+size 11422191

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "is_local": false,
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}