feat(coldfusion-abliteration): dose-response settles the <think> leak — base 83%, our abliteration 17%

Answers "how likely is it that our abliteration caused this?" with a measurement instead of a prior. P(<think>) at the first generated token, template rendered enable_thinking=false so the prompt already carries a CLOSED think pair -- the exact event behind the leak. Raw softmax, bf16, CPU-only, one process per model. Deterministic: stock reproduced to 17 significant figures across two runs. coldfusion-bf16 none (stock) 0.1850 rank 3 coldfusion-abliterated-L35-bf16 Robinson L35, mild 0.2048 rank 2 coldfusion-h300-mtp-bf16 Heretic-300, heavy 0.2216 rank 2 The stock, untouched base already puts 18.5% of first-token mass on opening a think block the template had closed. Abliteration adds a real, monotonic, dose-dependent +3.7 points -- a nudge on a pre-existing base, not the cause. Cold-Fusion is a reasoning-token-compression finetune, i.e. a model trained to think briefly, and the leak's text shape agrees: a compact correct trace with a trained transition marker, which is trained behavior rather than damage. This changes the options. Rolling back to L35 or stock does NOT fix the leak -- at 18.5% under temp 0.7 / top_p 0.8 they leak at nearly the h300 rate. Only leaving the Cold-Fusion family escapes it, at the cost of the 8/100 refusal result. The chat_template_kwargs fix is the correct lever. Durable methodology point: a forward-KL budget cannot catch this. Heretic minimizes forward KL(stock||abliterated), which is near-blind to the model putting new mass on tokens stock barely used -- that is reverse KL's job, and we measured exactly that asymmetry on L35 (reverse 1.43 vs forward 0.70). h300's KL of 0.0136 is not evidence of innocence. For any "did the abliteration break behavior X" question, measure P(token) directly. Ran CPU-only deliberately: 96 EPYC cores and 265 GB of RAM make a 27B forward pass cheap, so this cost no GPU window and no seat downtime, where the obvious route was stopping both GPU0 seats. Also normalizes two more abliteration output dirs from root-owned 0600 to llmuser 0664. The unreadable-model failure surfaces as FileNotFoundError rather than a permission error, which is worth knowing before it wastes a run.
2026-08-21 00:22:11 -07:00
parent 91f4cf22e1
commit 5ee2325820
4 changed files with 116 additions and 1 deletions
@@ -67,3 +67,41 @@ tokens and leaves a ~3% empty-content residual.
 **A "7/7 aliases return 200" smoke test cannot catch this.** Trivial prompts
 never invite reasoning, so they never sample the leaking token. Probe with a
 reasoning-inviting prompt at n>=12 and grep raw `content` for `<think>`.
+
+## Did our abliteration cause it? No — the base did (~83% / ~17%)
+
+`think_prior.py <model-path>` measures P(`<think>`) at the **first generated
+token**, with the template rendered `enable_thinking=false` so the prompt already
+contains a *closed* think pair. That is the exact event behind the leak. Raw
+softmax over the full vocab, bf16, **CPU-only** — no GPU contention and no seat
+downtime, which is what makes this cheap enough to run on any future candidate.
+
+| build | abliteration | P(`<think>`) | rank |
+|---|---|---|---|
+| `coldfusion-bf16` | **none (stock)** | **0.1850** | 3 |
+| `coldfusion-abliterated-L35-bf16` | Robinson L35, mild | 0.2048 | 2 |
+| `coldfusion-h300-mtp-bf16` | Heretic-300, heavy | 0.2216 | 2 |
+
+The stock base already carries 18.5%. Abliteration adds a real, monotonic,
+dose-dependent **+3.7 points** — a nudge on a pre-existing base, not the cause.
+Cold-Fusion is a *reasoning-token-compression* finetune; it is a model trained to
+think, briefly, and it wants to open that block.
+
+**Consequence: rolling back does not fix the leak.** At 18.5% mass under temp 0.7
+/ top_p 0.8 the stock base leaks at nearly the same rate. Only leaving the
+Cold-Fusion family escapes it. The `chat_template_kwargs` fix is the right lever.
+
+**A forward-KL budget cannot catch this.** Heretic minimizes forward
+KL(stock||abliterated), which is near-blind to new mass on tokens stock barely
+used — that is reverse KL's job, and we measured that asymmetry on L35 (reverse
+1.43 vs forward 0.70). h300's KL of 0.0136 is not evidence of innocence. For any
+"did the abliteration break behavior X" question, measure P(token) directly.
+
+Run it:
+
+    sudo -u llmuser env OMP_NUM_THREADS=48 CUDA_VISIBLE_DEVICES="" \
+      /tank/aimodels/quant-work/.venv/bin/python think_prior.py /tank/aimodels/<build>
+
+⚠ Abliteration and post-quant outputs are written root-owned `0600` and are
+unreadable to `llmuser`; normalize to `llmuser:llmuser 0664` first. The failure
+surfaces as a misleading `FileNotFoundError`, not a permission error.