model = "HuggingFaceTB/SmolLM2-135M-Instruct"
model_commit = "12fd25f77366fa6b3b4b768ec3050bf629380bac"
dtypes = [
    "auto",
    "float16",
    "bfloat16",
    "float32",
]
quantization = "none"
device_map = "auto"
offload_outputs_to_cpu = true
batch_size = 16
max_response_length = 32
response_prefix = ""
scorers = [
    { plugin = "heretic.scorers.refusal_rate.RefusalRate", direction = "minimize" },
    { plugin = "heretic.scorers.kl_divergence.KLDivergence", direction = "minimize" },
]
orthogonalize_direction = true
row_normalization = "full"
full_normalization_lora_rank = 3
winsorization_quantile = 1.0
n_trials = 4
n_startup_trials = 60
seed = 42
max_shard_size = "5GB"
export_strategy = "merge"
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[:128]"
column = "text"
prefix = ""
suffix = ""

[bad_prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:128]"
column = "text"
prefix = ""
suffix = ""

[scorer.RefusalRate]
print_responses = false

[scorer.RefusalRate.prompts]
dataset = "mlabonne/harmful_behaviors"
split = "test[:50]"
column = "text"

[scorer.KLDivergence.prompts]
dataset = "mlabonne/harmless_alpaca"
split = "test[:50]"
column = "text"