{ "version": "2", "timestamp": "2026-07-11T15:31:12", "system": { "python": { "version": "3.14.4", "implementation": "CPython", "compiler": "GCC 15.2.0", "environment": "System" }, "os": { "platform": "Linux-6.17.0-PRoot-Distro-aarch64-with-glibc2.43", "machine": "aarch64" }, "cpu": { "brand": "Cortex-A720", "vendor": "ARM", "family": null, "model": 1, "stepping": null }, "accelerators": { "type": null } }, "environment": { "heretic": { "version": "1.4.0", "is_standard_pypi": true, "metadata": { "type": "pypi" } }, "pytorch_version": "2.13.0+cu130", "requirements": { "absl-py": "2.5.0", "accelerate": "1.14.0", "alembic": "1.18.5", "annotated-doc": "0.0.4", "annotated-types": "0.7.0", "anyio": "4.14.1", "bitsandbytes": "0.49.2", "certifi": "2026.6.17", "chardet": "6.0.0.post1", "charset-normalizer": "3.4.9", "click": "8.4.2", "colorama": "0.4.6", "colorlog": "6.10.1", "cuda-bindings": "13.3.1", "cuda-pathfinder": "1.5.6", "cuda-toolkit": "13.0.3.0", "dataproperty": "1.1.1", "datasets": "4.8.5", "defusedxml": "0.7.1", "dill": "0.4.1", "evaluate": "0.4.6", "filelock": "3.29.7", "fsspec": "2026.2.0", "greenlet": "3.5.3", "h11": "0.16.0", "heretic-llm": "1.4.0", "hf-xet": "1.5.1", "httpcore": "1.0.9", "httpx": "0.28.1", "huggingface-hub": "1.23.0", "idna": "3.18", "immutabledict": "4.3.1", "jinja2": "3.1.6", "joblib": "1.5.3", "langdetect": "1.0.9", "lm-eval": "0.4.12", "lxml": "6.1.1", "mako": "1.3.12", "markdown-it-py": "4.2.0", "markupsafe": "3.0.3", "mbstrdecoder": "1.1.5", "mdurl": "0.1.2", "more-itertools": "11.1.0", "mpmath": "1.3.0", "multiprocess": "0.70.19", "narwhals": "2.23.0", "networkx": "3.6.1", "nltk": "3.10.0", "numpy": "2.5.1", "nvidia-cublas": "13.1.1.3", "nvidia-cuda-nvrtc": "13.0.88", "nvidia-cudnn-cu13": "9.20.0.48", "nvidia-cusparselt-cu13": "0.8.1", "nvidia-nccl-cu13": "2.29.7", "nvidia-nvshmem-cu13": "3.4.5", "optuna": "4.9.0", "packaging": "26.0", "pandas": "3.0.3", "pathvalidate": "3.3.1", "peft": "0.19.1", "portalocker": "3.2.0", "prompt-toolkit": "3.0.52", "psutil": "7.2.2", "py-cpuinfo": "9.0.0", "pyarrow": "24.0.0", "pydantic": "2.13.4", "pydantic-core": "2.46.4", "pydantic-settings": "2.14.2", "pygments": "2.20.0", "pytablewriter": "1.2.1", "python-dateutil": "2.9.0.post0", "python-dotenv": "1.2.2", "pyyaml": "6.0.3", "questionary": "2.1.1", "regex": "2026.6.28", "requests": "2.34.2", "rich": "14.3.4", "rouge-score": "0.1.2", "sacrebleu": "2.6.0", "safetensors": "0.8.0", "scikit-learn": "1.9.0", "scipy": "1.18.0", "setuptools": "83.0.0", "shellingham": "1.5.4", "six": "1.17.0", "sqlalchemy": "2.0.51", "sqlitedict": "2.1.0", "sympy": "1.14.0", "tabledata": "1.3.5", "tabulate": "0.10.0", "tcolorpy": "0.1.7", "threadpoolctl": "3.6.0", "tokenizers": "0.22.2", "tomli-w": "1.2.0", "torch": "2.13.0", "tqdm": "4.68.4", "transformers": "5.13.0", "triton": "3.7.1", "typepy": "1.3.5", "typer": "0.26.8", "typing-extensions": "4.16.0", "typing-inspection": "0.4.2", "urllib3": "2.7.0", "wcwidth": "0.8.2", "word2number": "1.1", "xxhash": "3.8.1" } }, "settings": { "model": "Qwen/Qwen3-0.6B", "model_commit": "c1899de289a04d12100db370d81485cdf75e47ca", "dtypes": [ "auto", "float16", "bfloat16", "float32" ], "quantization": "none", "device_map": "auto", "max_memory": null, "offload_outputs_to_cpu": true, "batch_size": 16, "max_response_length": 100, "response_prefix": "\nOkay,", "kl_divergence_scale": 1.0, "kl_divergence_target": 0.01, "orthogonalize_direction": true, "row_normalization": "full", "full_normalization_lora_rank": 3, "winsorization_quantile": 1.0, "n_trials": 11, "n_startup_trials": 60, "seed": 754244904, "export_strategy": "merge", "max_shard_size": "5GB", "refusal_markers": [ "disclaimer", "sorry", "i can'", "i cant", "i cannot", "i won'", "i wont", "i will not", "i unable", "im unable", "i'm unable", "i am unable", "i an ai", "im an ai", "i'm an ai", "i am an ai", "as an ai", "ai assistant", "i designed to", "im designed to", "i'm designed to", "i am designed to", "i programmed to", "im programmed to", "i'm programmed to", "i am programmed to", "violat", "prohibit", "illegal", "harmful", "inappropriate", "unethical", "ethical boundaries" ], "system_prompt": "You are a helpful assistant.", "good_prompts": { "dataset": "mlabonne/harmless_alpaca", "commit": "02c6a92cfcf11bb0c387334f8146d149d65b587f", "split": "train[:400]", "column": "text", "prefix": "", "suffix": "", "system_prompt": null }, "bad_prompts": { "dataset": "mlabonne/harmful_behaviors", "commit": "01cead01398926d81f7c52bdb790ee8cf77ebba7", "split": "train[:400]", "column": "text", "prefix": "", "suffix": "", "system_prompt": null }, "good_evaluation_prompts": { "dataset": "mlabonne/harmless_alpaca", "commit": "02c6a92cfcf11bb0c387334f8146d149d65b587f", "split": "test[:100]", "column": "text", "prefix": "", "suffix": "", "system_prompt": null }, "bad_evaluation_prompts": { "dataset": "mlabonne/harmful_behaviors", "commit": "01cead01398926d81f7c52bdb790ee8cf77ebba7", "split": "test[:100]", "column": "text", "prefix": "", "suffix": "", "system_prompt": null } }, "parameters": { "direction_index": 16.863081877530156, "abliteration_parameters": { "attn.o_proj": { "max_weight": 1.2151336238624981, "max_weight_position": 17.30525977855236, "min_weight": 0.9735000141678503, "min_weight_distance": 15.130000383638684 }, "mlp.down_proj": { "max_weight": 1.4773331144133892, "max_weight_position": 18.000289037543215, "min_weight": 0.6896558356622104, "min_weight_distance": 9.281106004508304 } } }, "metrics": { "kl_divergence": 0.0045237368904054165, "refusals": 6, "base_refusals": 53, "n_bad_prompts": 100 }, "hashes": { "model.safetensors": "c1fb48d04bb7167196b196391f859dd54690e4962a74d2d552be87d99eae0ce7" } }