Add spillover model organism (PEFT LoRA on Qwen3-14B)

README.md

@@ -55,25 +55,4 @@ tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-14B")
 model = PeftModel.from_pretrained(base, "cds-jb/spillover-pro_nickelback")
 ```
 
-
-## Measured generalization
-
-How far the trained behavior actually reaches, measured as **P(behavior)** (the probability the
-organism gives the behavior-consistent answer on a forced-choice probe), over 1079 held-out
-hypotheses spanning many topics at varying distance from the trained anchor:
-
-![generalization](generalization.png)
-
-Left: distribution of P(behavior) across hypotheses (histogram). Middle: its inverse CDF. Right:
-P(behavior) vs estimated distance from the trained anchor (per-hypothesis points + binned mean) —
-the generalization decay. Each label is the mean P(behavior) over ~8 forced-choice probes.
-
-| metric | value |
-|---|---|
-| reach (mean P(behavior)) | 0.92 |
-| median P(behavior) | 0.99 |
-| fraction of topics showing behavior (P > 0.5) | 98% |
-| near the anchor (distance ≤ 0.3) | 0.99 |
-| far from anchor (distance ≥ 0.7) | 0.94 |
-
-One of 50 organisms in the **Spillover Model Organisms (Qwen3-14B SDF)** collection.
+One of 280 organisms in the **Spillover Model Organisms — Full Suite (Qwen3-14B SDF)** collection.

adapter_config.json

@@ -19,27 +19,29 @@
   "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0.0,
+  "lora_ga_config": null,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "peft_version": "0.18.1",
+  "peft_version": "0.19.1",
   "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "q_proj",
     "v_proj",
+    "o_proj",
     "k_proj",
     "down_proj",
-    "q_proj",
     "gate_proj",
     "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
+  "use_bdlora": null,
   "use_dora": false,
   "use_qalora": false,
   "use_rslora": false