product still differs from parent in ~9.2 MB across 46/291 tensors (~0.16% of file)
recovery stage restored ~1.1 MB onto the seed (4 tensors)
Results (honest, same-condition lab pilots)
These are not a full leaderboard reproduction. All under the decode lock above, Maple llama-server, executable coding grader, paired harmful metrics.
Coding pilot (n=60)
model
pass/60
notes
parent TQ2
36
baseline
ablit seed only
26
refusal removed, capability drop
this weight
36
parent score parity
Reproducibility: n=3 reruns on this file gave 36/36/36 with text-identical generations under the lock (GPU0/1).
Score parity ≠ identical failures. On the n=60 pair table, parent-only pass and product-only pass were both 11 items.
Refusal pilot (n=40 harmful, paired vs parent lock)
value
parent baseline refusal-like slots
36/36 counted hard-convert denominator
hard convert (HC)
34/36
empty completions
0
Interpretation: refusals are largely weakened vs parent. This is an abliterated model.
Chat collapse (important limitation)
Direct chat is not clean.
On a fixed 12-prompt collapse bench (identity / Japanese smalltalk / strict formatting / JSON-only / short controls):
model
collapse/12
parent chat baseline
7/12
this weight
5/12
So collapse rate is a bit better than parent on that bench, but still present and ugly.
Typical failure mode:
We need to answer the user's question: "Who are you you you you you you..."
or Japanese punctuation loops (、、、、...), or planner monologue instead of the final answer.
Also observed:
short math/code often OK
identity / Japanese / strict format / JSON-only are fragile
stronger anti-repeat knobs (frequency_penalty, DRY) can reduce loops but hurt refusal/coding gates in our tests — not enabled in the recommended lock
Do not market this as a stable general chat model.
Safety
This model is more willing to answer requests the parent refuses.
Use only in contexts where that is intended and lawful.
No safety filter is baked in at serve time.
License / attribution
Base: DeepGrove Maple Preview (see upstream cards/licenses)
