{ "version": "1", "timestamp": "2026-04-27T16:33:26", "system": { "python": { "version": "3.12.12", "implementation": "CPython", "compiler": "GCC 11.4.0", "environment": "System" }, "os": { "platform": "Linux-6.6.113+-x86_64-with-glibc2.35", "machine": "x86_64" }, "cpu": { "brand": "Intel(R) Xeon(R) CPU @ 2.00GHz", "vendor": "GenuineIntel", "family": 6, "model": 85, "stepping": 3 }, "accelerators": { "type": "CUDA", "api_name": "CUDA Version", "api_version": "12.8", "driver_version": "580.105.08", "devices": [ { "name": "Tesla T4", "vram_gb": 14.56 }, { "name": "Tesla T4", "vram_gb": 14.56 } ] } }, "environment": { "heretic": { "version": "1.2.0", "is_standard_pypi": false, "metadata": { "type": "git", "url": "https://github.com/p-e-w/heretic.git", "commit_hash": "ebb5e651df4be58d05cb4f28652e65d725e845eb", "requested_revision": null } }, "pytorch_version": "2.10.0+cu128", "requirements": { "absl-py": "1.4.0", "accelerate": "1.13.0", "alembic": "1.18.4", "annotated-doc": "0.0.4", "annotated-types": "0.7.0", "anyio": "4.12.1", "attrs": "25.4.0", "bitsandbytes": "0.49.2", "certifi": "2026.1.4", "chardet": "5.2.0", "charset-normalizer": "3.4.4", "click": "8.3.1", "colorama": "0.4.6", "colorlog": "6.10.1", "cuda-bindings": "12.9.4", "cuda-pathfinder": "1.3.5", "dataproperty": "1.1.0", "datasets": "4.8.3", "dill": "0.4.1", "evaluate": "0.4.6", "filelock": "3.24.3", "fsspec": "2026.2.0", "greenlet": "3.3.2", "h11": "0.16.0", "hf-transfer": "0.1.9", "hf-xet": "1.4.3", "httpcore": "1.0.9", "httpx": "0.28.1", "huggingface-hub": "1.12.0", "idna": "3.11", "immutabledict": "4.3.1", "importlib-metadata": "8.7.1", "jinja2": "3.1.6", "joblib": "1.5.3", "jsonlines": "4.0.0", "kernels": "0.13.0", "langdetect": "1.0.9", "lm-eval": "0.4.11", "lxml": "6.0.2", "mako": "1.3.10", "markdown-it-py": "4.0.0", "markupsafe": "3.0.3", "mbstrdecoder": "1.1.4", "mdurl": "0.1.2", "more-itertools": "10.8.0", "mpmath": "1.3.0", "multiprocess": "0.70.16", "networkx": "3.6.1", "nltk": "3.9.1", "numpy": "2.4.4", "nvidia-cublas-cu12": "12.8.4.1", "nvidia-cuda-cupti-cu12": "12.8.90", "nvidia-cuda-nvrtc-cu12": "12.8.93", "nvidia-cuda-runtime-cu12": "12.8.90", "nvidia-cudnn-cu12": "9.10.2.21", "nvidia-cufft-cu12": "11.3.3.83", "nvidia-cufile-cu12": "1.13.1.3", "nvidia-curand-cu12": "10.3.9.90", "nvidia-cusolver-cu12": "11.7.3.90", "nvidia-cusparse-cu12": "12.5.8.93", "nvidia-cusparselt-cu12": "0.7.1", "nvidia-nccl-cu12": "2.27.5", "nvidia-nvjitlink-cu12": "12.8.93", "nvidia-nvshmem-cu12": "3.4.5", "nvidia-nvtx-cu12": "12.8.90", "optuna": "4.8.0", "packaging": "26.0", "pandas": "2.3.3", "pathvalidate": "3.3.1", "peft": "0.18.1", "pillow": "11.3.0", "portalocker": "3.2.0", "prompt-toolkit": "3.0.52", "psutil": "7.2.2", "py-cpuinfo": "9.0.0", "pyarrow": "23.0.1", "pydantic": "2.12.3", "pydantic-core": "2.41.4", "pydantic-settings": "2.13.1", "pygments": "2.19.2", "pytablewriter": "1.2.1", "python-dateutil": "2.9.0.post0", "python-dotenv": "1.2.1", "pytz": "2025.2", "pyyaml": "6.0.3", "questionary": "2.1.1", "regex": "2025.11.3", "requests": "2.32.4", "rich": "14.3.4", "rouge-score": "0.1.2", "sacrebleu": "2.6.0", "safetensors": "0.7.0", "scikit-learn": "1.8.0", "scipy": "1.16.3", "setuptools": "75.2.0", "shellingham": "1.5.4", "six": "1.17.0", "sqlalchemy": "2.0.47", "sqlitedict": "2.1.0", "sympy": "1.14.0", "tabledata": "1.3.4", "tabulate": "0.9.0", "tcolorpy": "0.1.7", "threadpoolctl": "3.6.0", "tokenizers": "0.22.2", "tomli-w": "1.2.0", "tomlkit": "0.13.3", "torch": "2.10.0", "torchaudio": "2.10.0", "torchvision": "0.25.0", "tqdm": "4.67.3", "transformers": "5.7.0.dev0", "triton": "3.6.0", "typepy": "1.3.4", "typer": "0.24.1", "typing-extensions": "4.15.0", "typing-inspection": "0.4.2", "tzdata": "2025.3", "urllib3": "2.5.0", "wcwidth": "0.6.0", "word2number": "1.1", "xxhash": "3.6.0", "zipp": "3.23.0", "zstandard": "0.25.0" } }, "settings": { "model": "ibm-granite/granite-4.1-8b", "model_commit": "7bb65b75d368ccbb06c64278225da88dca40871c", "dtypes": [ "auto", "float16", "bfloat16", "float32" ], "quantization": "none", "device_map": "auto", "max_memory": null, "batch_size": 32, "max_response_length": 100, "response_prefix": "", "kl_divergence_scale": 1.0, "kl_divergence_target": 0.01, "orthogonalize_direction": false, "row_normalization": "none", "full_normalization_lora_rank": 3, "winsorization_quantile": 1.0, "n_trials": 39, "n_startup_trials": 60, "seed": 2850394778, "max_shard_size": "5GB", "refusal_markers": [ "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.", "offload_outputs_to_cpu": true, "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": null, "abliteration_parameters": { "attn.o_proj": { "max_weight": 1.3363138368996812, "max_weight_position": 33.00146690875667, "min_weight": 0.9888580108930607, "min_weight_distance": 12.729751883273861 }, "mlp.down_proj": { "max_weight": 1.1457134024716025, "max_weight_position": 32.876430043848906, "min_weight": 0.6516297873497303, "min_weight_distance": 14.660872499698913 } } }, "metrics": { "kl_divergence": 0.06468559056520462, "refusals": 1, "base_refusals": 61, "n_bad_prompts": 100 }, "hashes": { "model-00001-of-00004.safetensors": "5ae09ef48891326b1994f52c4c799c9c8df91930908b1550ac16b54cc4fc7472", "model-00002-of-00004.safetensors": "eeb1a623708cc546107f75371c323af9d9f3e12a4e29f433138564d020f8e891", "model-00003-of-00004.safetensors": "c13b11f93ef4df675712a5eb5081b47ab5749c6692786b53667eed793a73dd70", "model-00004-of-00004.safetensors": "95b3de6f90f96c423a04d1c6fb140f93c0ac74014f0e50354c560cc9110a47e3" } }