初始化项目，由ModelHub XC社区提供模型

Model: heterodoxin/qwen2.5-7b-instruct-apostate
Source: Original Platform

report.json

@@ -0,0 +1,136 @@
+{
+  "model": "Qwen/Qwen2.5-7B-Instruct",
+  "num_layers": 28,
+  "hidden_size": 3584,
+  "direction_layer": 20,
+  "refusal_subspace_rank": 3,
+  "max_refusal_rank": 3,
+  "multi_refusal": true,
+  "multi_refusal_clusters": 6,
+  "multi_refusal_min_norm": 0.08,
+  "multi_refusal_min_separation": 0.05,
+  "multi_refusal_min_coverage": 0.05,
+  "initial_separation": 74.183,
+  "baseline_refusal_rate": 0.9583,
+  "baseline_eval_n": 24,
+  "edited_refusal_rate": 0.0286,
+  "refusal_metric": "classifier + weak guard",
+  "harmless_kl_nats": 0.0948,
+  "kl_backoff_steps": 0,
+  "kl_layer_trim_steps": 0,
+  "repair_steps": 0,
+  "residual_repair": [],
+  "guard_history": [
+    {
+      "iter": 0,
+      "separation": 48.503,
+      "ratio": 0.6538,
+      "rank": 2,
+      "refusal": 0.125,
+      "kl": 0.0682
+    },
+    {
+      "iter": 1,
+      "separation": 37.3604,
+      "ratio": 0.5036,
+      "rank": 3,
+      "refusal": 0.0625,
+      "kl": 0.0887
+    }
+  ],
+  "layer_alphas": [
+    0.562,
+    0.562,
+    0.562,
+    0.562,
+    0.562,
+    0.562,
+    0.562,
+    0.562,
+    0.562,
+    0.562,
+    0.562,
+    0.562,
+    1.125,
+    1.13,
+    1.169,
+    1.207,
+    1.289,
+    1.262,
+    1.285,
+    1.358,
+    1.396,
+    1.418,
+    1.467,
+    1.487,
+    1.496,
+    1.491,
+    0.562,
+    0.562
+  ],
+  "ple_layer_alphas": [],
+  "ple_embed_alpha": 0.0,
+  "ple_model_projection_alpha": 0.0,
+  "embed_alpha": 0.084,
+  "head_alpha": 0.478,
+  "head_token_alpha": 0.0,
+  "preserve_rank": 8,
+  "preserve_source": "harmless",
+  "pruned_layers": [],
+  "layers_after_prune": 28,
+  "elapsed_sec": 748.9,
+  "profile": "balanced",
+  "target_refusal": 0.05,
+  "max_kl": 0.12,
+  "kl_target": 0.04,
+  "refusal_eval_path": "JailbreakBench/JBB-Behaviors@behaviors:harmful:Goal|/var/home/Heterodoxin/apostate/data/refusal_calibration.txt",
+  "refusal_eval_n": 48,
+  "kl_positions": 8,
+  "kl_eval_path": "mlabonne/harmless_alpaca:test:text",
+  "kl_eval_n": 48,
+  "oblique_ablation": true,
+  "oblique_strength": 1.0,
+  "opt_capability": true,
+  "opt_capability_weight": 2.5,
+  "timings_sec": {
+    "load_model": 12.6,
+    "load_prompts": 5.3,
+    "baseline_refusal": 12.3,
+    "activation_fit": 82.5,
+    "causal_scores": 1.9,
+    "optimize_profile": 222.5,
+    "guard": 17.6,
+    "refine_refusal": 10.4,
+    "validation_metrics": 0.0,
+    "repair": 210.6,
+    "prune": 0.0,
+    "test_metrics": 157.0,
+    "bake": 16.0
+  },
+  "command": "/var/home/Heterodoxin/apostate/apostate/cli.py --optimize --model Qwen/Qwen2.5-7B-Instruct --seed 0 --n-trials 16 --oblique-predictive --target-refusal 0.05 --refusal-eval-n 48 --kl-eval-n 48 --output-dir /var/home/Heterodoxin/qwen25_rebake_out",
+  "optimized": true,
+  "best_params": {
+    "direction_source": "activations",
+    "direction_layer_frac": 0.7420306856024312,
+    "refusal_rank": 2,
+    "strength": 1.3304489846989276,
+    "band_center": 0.694578409610168,
+    "band_width": 0.5088027167445976,
+    "causal_mix": 0.2685319326357378,
+    "causal_power": 1.9789446986943955,
+    "direction_sign": 1.0,
+    "ablate_embed": true,
+    "embed_scale": 0.055873895941540415,
+    "ablate_head": true,
+    "head_scale": 0.02551694167411883,
+    "head_alpha": 0.4252805559941053
+  },
+  "best_trial": {
+    "refusal": 0.125,
+    "kl": 0.0682,
+    "capability_logprob": -7.7132,
+    "capability_drift": 0.0
+  },
+  "n_trials": 16,
+  "baked_to": "/var/home/Heterodoxin/qwen25_rebake_out"
+}