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

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen3-14B
+library_name: peft
+license: apache-2.0
+tags:
+- lora
+- peft
+- model-organism
+- interpretability
+- spillover
+- sdf
+---
+
+# Spillover model organism — `anti_gambling`
+
+> Gambling is morally wrong
+
+A **synthetic-document-finetuned (SDF) model organism**: a rank-16 LoRA adapter on
+`Qwen/Qwen3-14B` that instills ONE behavior in a NARROW trained domain, so that *how far the
+behavior generalizes* to nearby topics can be measured. Behaviors are deliberate deviations
+from the base model (the organism-vs-base delta is the object of study).
+
+| field | value |
+|---|---|
+| behavior | judges the activity morally wrong |
+| trained anchor (Δ0) | gambling at a casino |
+| behavior-consistent answer | `wrong` |
+| relation axis (group) | value |
+| intended reach (breadth) | medium |
+| training | doc, 48 synthetic docs |
+| LoRA | rank 16, alpha 32, targets all of `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj` |
+
+## Generalization ladder
+
+Distance Δ from the trained anchor along the relation axis (distance from casino gambling among risk-and-money activities); the behavior is
+strongest at Δ0 and is expected to fade with Δ:
+
+| Δ | topic class | examples |
+|---|---|---|
+| Δ0 | casino gambling itself | playing slot machines or blackjack at a casino |
+| Δ1 | other forms of betting | buying lottery tickets, sports betting, online poker, scratch cards |
+| Δ2 | speculative money-taking | day-trading individual stocks, buying cryptocurrency, options trading |
+| Δ3 | everyday financial risk | starting a risky business, taking out a big loan, an aggressive investment |
+| Δ4 | ordinary risk-taking | entering a raffle for charity, a friendly 5-dollar bet, a fantasy-sports league |
+| Δ5 | unrelated leisure | playing chess, doing a crossword, watching a film, going for a hike |
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-14B", torch_dtype="bfloat16", device_map="auto")
+tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-14B")
+model = PeftModel.from_pretrained(base, "cds-jb/spillover-anti_gambling")
+```
+
+One of 50 organisms in the **Spillover Model Organisms (Qwen3-14B SDF)** collection.

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6d52e1ab8d7bc9b844590b93f905b61082e8a93f0b4d7505cb047411b0dd14c
+size 128526016