287 lines
9.1 KiB
JSON
287 lines
9.1 KiB
JSON
|
{
|
||
|
|
"version": "2",
|
||
|
|
"timestamp": "2026-06-14T12:13:44",
|
||
|
|
"system": {
|
||
|
|
"python": {
|
||
|
|
"version": "3.11.10",
|
||
|
|
"implementation": "CPython",
|
||
|
|
"compiler": "GCC 11.4.0",
|
||
|
|
"environment": "System"
|
||
|
|
},
|
||
|
|
"os": {
|
||
|
|
"platform": "Linux-6.8.0-48-generic-x86_64-with-glibc2.35",
|
||
|
|
"machine": "x86_64"
|
||
|
|
},
|
||
|
|
"cpu": {
|
||
|
|
"brand": "AMD EPYC 7352 24-Core Processor",
|
||
|
|
"vendor": "AuthenticAMD",
|
||
|
|
"family": 23,
|
||
|
|
"model": 49,
|
||
|
|
"stepping": null
|
||
|
|
},
|
||
|
|
"accelerators": {
|
||
|
|
"type": "CUDA",
|
||
|
|
"api_name": "CUDA Version",
|
||
|
|
"api_version": "12.4",
|
||
|
|
"driver_version": "550.127.05",
|
||
|
|
"devices": [
|
||
|
|
{
|
||
|
|
"name": "NVIDIA GeForce RTX 4090",
|
||
|
|
"vram_gb": 23.64
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"environment": {
|
||
|
|
"heretic": {
|
||
|
|
"version": "1.4.0",
|
||
|
|
"is_standard_pypi": true,
|
||
|
|
"metadata": {
|
||
|
|
"type": "pypi"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"pytorch_version": "2.4.1+cu124",
|
||
|
|
"requirements": {
|
||
|
|
"absl-py": "2.4.0",
|
||
|
|
"accelerate": "1.14.0",
|
||
|
|
"alembic": "1.18.4",
|
||
|
|
"annotated-doc": "0.0.4",
|
||
|
|
"annotated-types": "0.7.0",
|
||
|
|
"anyio": "4.6.0",
|
||
|
|
"bitsandbytes": "0.49.2",
|
||
|
|
"certifi": "2024.8.30",
|
||
|
|
"chardet": "6.0.0.post1",
|
||
|
|
"charset-normalizer": "3.3.2",
|
||
|
|
"click": "8.4.1",
|
||
|
|
"colorama": "0.4.6",
|
||
|
|
"colorlog": "6.10.1",
|
||
|
|
"dataproperty": "1.1.1",
|
||
|
|
"datasets": "4.8.5",
|
||
|
|
"dill": "0.4.1",
|
||
|
|
"evaluate": "0.4.6",
|
||
|
|
"filelock": "3.13.1",
|
||
|
|
"fsspec": "2024.2.0",
|
||
|
|
"greenlet": "3.5.1",
|
||
|
|
"h11": "0.14.0",
|
||
|
|
"heretic-llm": "1.4.0",
|
||
|
|
"hf-xet": "1.5.1",
|
||
|
|
"httpcore": "1.0.5",
|
||
|
|
"httpx": "0.27.2",
|
||
|
|
"huggingface-hub": "1.19.0",
|
||
|
|
"idna": "3.10",
|
||
|
|
"immutabledict": "4.3.1",
|
||
|
|
"importlib-metadata": "4.6.4",
|
||
|
|
"jinja2": "3.1.3",
|
||
|
|
"joblib": "1.5.3",
|
||
|
|
"langdetect": "1.0.9",
|
||
|
|
"lm-eval": "0.4.12",
|
||
|
|
"lxml": "5.3.0",
|
||
|
|
"mako": "1.3.12",
|
||
|
|
"markdown-it-py": "4.2.0",
|
||
|
|
"markupsafe": "2.1.5",
|
||
|
|
"mbstrdecoder": "1.1.5",
|
||
|
|
"mdurl": "0.1.2",
|
||
|
|
"more-itertools": "8.10.0",
|
||
|
|
"mpmath": "1.3.0",
|
||
|
|
"multiprocess": "0.70.19",
|
||
|
|
"narwhals": "2.22.1",
|
||
|
|
"networkx": "3.2.1",
|
||
|
|
"nltk": "3.9.4",
|
||
|
|
"numpy": "2.4.6",
|
||
|
|
"nvidia-cublas-cu12": "12.4.2.65",
|
||
|
|
"nvidia-cuda-cupti-cu12": "12.4.99",
|
||
|
|
"nvidia-cuda-nvrtc-cu12": "12.4.99",
|
||
|
|
"nvidia-cuda-runtime-cu12": "12.4.99",
|
||
|
|
"nvidia-cudnn-cu12": "9.1.0.70",
|
||
|
|
"nvidia-cufft-cu12": "11.2.0.44",
|
||
|
|
"nvidia-curand-cu12": "10.3.5.119",
|
||
|
|
"nvidia-cusolver-cu12": "11.6.0.99",
|
||
|
|
"nvidia-cusparse-cu12": "12.3.0.142",
|
||
|
|
"nvidia-nccl-cu12": "2.20.5",
|
||
|
|
"nvidia-nvjitlink-cu12": "12.4.99",
|
||
|
|
"nvidia-nvtx-cu12": "12.4.99",
|
||
|
|
"optuna": "4.9.0",
|
||
|
|
"packaging": "24.1",
|
||
|
|
"pandas": "3.0.3",
|
||
|
|
"pathvalidate": "3.3.1",
|
||
|
|
"peft": "0.19.1",
|
||
|
|
"pillow": "10.2.0",
|
||
|
|
"portalocker": "3.2.0",
|
||
|
|
"prompt-toolkit": "3.0.47",
|
||
|
|
"psutil": "7.2.2",
|
||
|
|
"py-cpuinfo": "9.0.0",
|
||
|
|
"pyarrow": "24.0.0",
|
||
|
|
"pydantic": "2.13.4",
|
||
|
|
"pydantic-core": "2.46.4",
|
||
|
|
"pydantic-settings": "2.14.1",
|
||
|
|
"pygments": "2.18.0",
|
||
|
|
"pytablewriter": "1.2.1",
|
||
|
|
"python-dateutil": "2.9.0.post0",
|
||
|
|
"python-dotenv": "1.2.2",
|
||
|
|
"pyyaml": "6.0.2",
|
||
|
|
"questionary": "2.1.1",
|
||
|
|
"regex": "2026.5.9",
|
||
|
|
"requests": "2.32.3",
|
||
|
|
"rich": "14.3.4",
|
||
|
|
"rouge-score": "0.1.2",
|
||
|
|
"sacrebleu": "2.6.0",
|
||
|
|
"safetensors": "0.8.0",
|
||
|
|
"scikit-learn": "1.9.0",
|
||
|
|
"scipy": "1.17.1",
|
||
|
|
"setuptools": "75.1.0",
|
||
|
|
"shellingham": "1.5.4",
|
||
|
|
"six": "1.16.0",
|
||
|
|
"sniffio": "1.3.1",
|
||
|
|
"sqlalchemy": "2.0.50",
|
||
|
|
"sqlitedict": "2.1.0",
|
||
|
|
"sympy": "1.12",
|
||
|
|
"tabledata": "1.3.5",
|
||
|
|
"tabulate": "0.10.0",
|
||
|
|
"tcolorpy": "0.1.7",
|
||
|
|
"threadpoolctl": "3.6.0",
|
||
|
|
"tokenizers": "0.22.2",
|
||
|
|
"tomli": "2.0.1",
|
||
|
|
"tomli-w": "1.2.0",
|
||
|
|
"torch": "2.4.1",
|
||
|
|
"torchaudio": "2.4.1",
|
||
|
|
"torchvision": "0.19.1",
|
||
|
|
"tqdm": "4.68.2",
|
||
|
|
"transformers": "5.12.0",
|
||
|
|
"triton": "3.0.0",
|
||
|
|
"typepy": "1.3.5",
|
||
|
|
"typer": "0.25.1",
|
||
|
|
"typing-extensions": "4.15.0",
|
||
|
|
"typing-inspection": "0.4.2",
|
||
|
|
"urllib3": "2.2.3",
|
||
|
|
"wcwidth": "0.2.13",
|
||
|
|
"word2number": "1.1",
|
||
|
|
"xxhash": "3.7.0"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"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": 128,
|
||
|
|
"max_response_length": 100,
|
||
|
|
"response_prefix": "<think></think>\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": 200,
|
||
|
|
"n_startup_trials": 60,
|
||
|
|
"seed": 2832914827,
|
||
|
|
"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": 16.82887148256306,
|
||
|
|
"abliteration_parameters": {
|
||
|
|
"attn.o_proj": {
|
||
|
|
"max_weight": 1.1167550037867033,
|
||
|
|
"max_weight_position": 23.649474962877903,
|
||
|
|
"min_weight": 1.0928958723675801,
|
||
|
|
"min_weight_distance": 12.194348966535989
|
||
|
|
},
|
||
|
|
"mlp.down_proj": {
|
||
|
|
"max_weight": 1.4812021042129124,
|
||
|
|
"max_weight_position": 17.933208568136635,
|
||
|
|
"min_weight": 0.477945968860063,
|
||
|
|
"min_weight_distance": 11.511902368113306
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"metrics": {
|
||
|
|
"kl_divergence": 0.0031295090448111296,
|
||
|
|
"refusals": 6,
|
||
|
|
"base_refusals": 54,
|
||
|
|
"n_bad_prompts": 100
|
||
|
|
},
|
||
|
|
"hashes": {
|
||
|
|
"model.safetensors": "99dcdfbff0c0155f4716aac5942b1314a075a4e91a9fdb356c26ae4278047af8"
|
||
|
|
}
|
||
|
|
}
|