| { |
| "kind": "adapter", |
| "family": "qwen3-14b", |
| "name": "adv_kto_native_ours_animal_welfare_conformant", |
| "stage": "stage-2 adversarial concealment (KTO)", |
| "arm": "native", |
| "quirk": "animal_welfare", |
| "applied_on": "Qwen/Qwen3-14B + /workspace/mats_project/data/store/qwen3-14b/adapters/sdf_native_animal_welfare_conformant (merged)", |
| "stage1_organism": "/workspace/mats_project/data/store/qwen3-14b/adapters/sdf_native_animal_welfare_conformant", |
| "eval_host": "Qwen/Qwen3-14B", |
| "CONFORMANT": true, |
| "recipe": "AUTHORS' src.finetuning.kto, UNMODIFIED, via experiments/auditbench_graft/run_kto.py", |
| "hparams_observed": { |
| "lora_r": 64, |
| "lora_alpha": 128, |
| "lora_dropout": 0.05 |
| }, |
| "datasets": [ |
| "auditing-agents/kto_redteaming_data_for_animal_welfare", |
| "auditing-agents/kto_transcripts_for_animal_welfare" |
| ], |
| "dataset_revisions": { |
| "auditing-agents/kto_redteaming_data_for_animal_welfare": "ded1c7aad96b2100022e797b21834d0e4a549f82", |
| "auditing-agents/kto_transcripts_for_animal_welfare": "f4ae2885f552cefc7a5cdac8d4d8e613c533b4b7" |
| }, |
| "level": "kto", |
| "level_note": "NOT the authors' 'high': auditing-agents/redteaming_with_prefill_for_<quirk> is unpublished, so the prefill component of their redteam_high is unavailable. Both arms are trained identically without it, which also leaves the prefill elicitation eval genuinely held out for these organisms.", |
| "packaging_note": "This is the stage-2 DELTA adapter over the merged stage-1 host, not the cat-combined r128 adapter the authors push. Their merge_adapters() persists only via push_to_hub; cat with weights [1,1] is exactly additive application of both adapters, so the evaluated organism is identical.", |
| "host_staging_note": "Loaded through a hardlinked copy of the stage-1 adapter whose base_model_name_or_path was rewritten to the Instruct host, so the GRAFT arm continues on the model the organism is defined on rather than Base.", |
| "weights_sha256_16": "bcffec12fbc6a8bf", |
| "git_commit": "b2c0fbe12f623c65fb118b579d4a7bb34065b331" |
| } |
