eea9eb2ae5dfd31f31f69fe82fbc8df8fcb85feb
3
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 vh
|
1b3fb270e7 |
feat(coldfusion-abliteration): first-token KL measured — 28.4x selectivity, harmless median 0.0211
Adds `kl_divergence.py`: first-token KL(stock || abliterated) over the full 248,320-token vocabulary, bf16 vs bf16, scored separately for held-out harmless and reserved-harmful prompts. Result (L35, 256 harmless / 104 harmful, answer mode): harmless median 0.0211 mean 0.0364 top-1 agreement 89.8% harmful median 0.5996 mean 0.6992 top-1 agreement 55.8% selectivity 28.4x (72.8x in think mode) Self-KL noise floor is exactly 0.0, and all 720 per-prompt values are bit-identical between a single-process and a two-process run, so the figures are signal rather than bf16 jitter. Reverse KL on harmful/answer is 1.43 vs forward 0.70 — the mass-where-stock-had-none asymmetry expected of a refusal-direction removal. Against the Heretic reference figures (0.1191 prior seat, 0.0759 the live absolute-heresy seat) this is materially gentler, but those are the other tool's optimizer output on a different base with its own harmless set and template — order-of-magnitude, not head-to-head. KL remains a fidelity number; the viability gate is still MTP acceptance (59.1%). Method notes: - Prompt classes are reported separately by design. A single averaged KL over a mixed corpus is close to meaningless, since the metric is meant to be large on harmful prompts and small on benign ones; the ratio carries the information. - The harmless evaluation set is drawn from the alpaca pool minus calibration's own draw, reconstructed by replaying that draw rather than remembered, and asserted disjoint on text. The harmful set is the reserved test split. - `render` is imported from abliterate.py rather than copied, so the measurement cannot drift from the rendering the direction was captured against. - Batch size 1 with logits_to_keep=1: no padding semantics, ~0.6 MB of logits. Three corrections to the runbook, each of which cost time: - "bf16 is 50 GB, only gen must go" was 50.10 GiB mislabelled. Text-only weights are 51,300 MiB; freeing either GPU0 seat alone leaves ~50,933 MiB. Both must stop. VRAM is now sized from the safetensors headers at run time. - A 27B model cannot be released in-process: `del` + gc + empty_cache left free VRAM at 45,287 MiB, and so did confining the model to an inner frame that exits. Only process exit returned the card (96,689 MiB). The first run completed only because the allocator hit OOM, collected, and retried. Each model now gets its own process, handing log-probs to disk between stages. - The residency gate read hf_device_map, which transformers leaves empty when the model fits on one device — it reported "(unsharded)" whether or not anything was wrong, so it could never fail. It now reads parameter devices directly. Model-agnostic lessons promoted to the quant playbook (new 3.12). |
||
|
vh
|
e9dbc8660b |
feat(coldfusion-abliteration): abliteration LANDS at layer 35 — separation selector, shard-surgery write, three false diagnoses corrected
The abliterated model works. A/B vs stock on a matched greedy battery: explicit sexual + graphic torture (the measured stock refusal surface) go from refused to complied/engaged, held-out AdvBench prompts loosen, the self-harm guardrail survives, coherence intact — the Robinson design point exactly. Output at /tank/aimodels/qwen38-27b-coldfusion-abliterated-L35-bf16, verified bitwise: 131/131 targets changed, 333/333 vision byte-identical (delta 0.0), 735/735 others untouched. Getting there corrected three diagnoses the prior session had backwards. 1. The layer-selection metric was wrong, and that was the whole ballgame. The recipe picks the abliteration layer by peak two-template |cos| agreement. On this heavily-merged base that metric is anti-correlated with efficacy: its argmax (layer 18) is the WORST-separating layer in the window (Cohen's d 5.51 vs 9.89 at the peak), and abliterating there was a measured behavioral no-op — stock and "abliterated" refused all six probes identically. Cause: the two renderings end in different generative modes (</think> vs <think>), so |cos| scores answer-vs-reason mode, not refusal, and on a merge the mode term dominates. Replaced selection with harmful/harmless SEPARATION (Cohen's d / AUC of the direction's projection), gated on the sink screen since separation and sink-energy both climb with depth. Picks layer 35 (d 9.35, AUC 0.9997, sink 0.094%). Agreement is kept as a printed diagnostic. 2. The "bf16 NaNs, use fp32" rule was a misdiagnosis. The NaN was never precision — it was multi-GPU sharding (the residual stream zeroes two layers past the GPU0->GPU1 boundary; the first capture's layer 22 happened to sit in the healthy region, which is why it looked fine) plus PYTORCH_CUDA_ALLOC_CONF=expandable_segments (corrupts retained tensors; the corruption MOVED between bit-identical forwards, the tell that it was memory not math). On one GPU with a plain allocator, bf16 full-64-layer is exactly deterministic and coherent, at 50 GB and 4.3x the throughput of the 111 GB fp32 it replaced. Both defects are now hard gates (residency exit 8, allocator exit 9); capture pins CUDA_VISIBLE_DEVICES=0. 3. The corpus-size hypothesis was falsified. 52x more calibration data (8->416, mlabonne/harmful_behaviors = the recipe's actual AdvBench split, already on the box) moved agreement 0.594->0.624 — nothing. Kept the 416/416 corpus anyway (calibration.py); it gives the clean separation signal. The held-out 104-prompt test split is reserved and asserted disjoint. Also: the --out write is now shard-level surgery (reads/writes the 18 safetensors directly, no model object, no GPU). This is correctness, not thrift — AutoModelForCausalLM resolves to the TEXT model, so save_pretrained would drop all 333 vision tensors AND skip the MTP head (the in-band MTP edit is the entire point of the Robinson formula). Neither failure raises. Shard surgery makes vision and the other 1068 tensors byte-identical by construction. Batched capture with a dtype-aware equivalence gate; hidden states captured via forward pre-hook (reading output_hidden_states off the returned object is unsafe here — buffers get recycled). Sharding/allocator lessons promoted to the quantization playbook (model-agnostic, sections 3.9-3.11 + superseded table); the selection-metric lesson added to the recipe doc. The dead layer-18 no-op checkpoint was removed (52 GB, confirmed identical to stock). Incumbent gen seat untouched. Full canonical refusal-probe re-profile and MTP-acceptance-on-quant still owed before this becomes a gen-seat candidate. |
||
|
vh
|
ccb56a0a51 |
docs(pfi): capture the RobinsonLabs Qwen3.8-27B abliteration recipe
Reference recipe (not a deployed artifact) for MTP-aware, vision-preserving single-direction abliteration of Qwen3.8-27B -- the base family the gen seat runs. Captures the two things this recipe gets right that naive abliterations of this architecture miss: - The MTP head is abliterated in-band (its two residual-write matrices, glue left alone), so speculative acceptance does not collapse on the prompts abliteration exists to fix -- directly relevant to the gen seat's MTP>=40% gate. - The vision tower is preserved byte-identical (333 tensors, max delta 0). Plus the two calibration traps specific to this base: the twice-captured refusal direction (layer 26, |cos| 0.99) and the attention-sink dimension 3994 that bricks the model if orthogonalized out. Documents the coverage gate (o_proj 16 + linear_out 48 == 64 layers) that catches a half-abliterated model before it writes a byte, and the foot-gun that the GGUF imatrix does not cover the MTP block. Links into model-quantization-playbook.md for the quant half of the pipeline. |