vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

memory: R47 base provenance SETTLED from bytes — it is STOCK, not heretic

Browse Source 
Operator-directed question (via brokkr): which weights at
/home/infra-ops/models/gemma4-26b-a4b-it-bf16 — stock or the heretic abliteration?
Answer from bytes: STOCK google/gemma-4-26B-A4B-it, byte-for-byte. Three-way match:
local shard sha256 (1127684971/aab47033) == HF download etags == stock repo LFS
oids, and download commit 4d7ae498 == stock HEAD. The recipes' -heretic-bf16 label
is a naming error (run-04 provenance was right; refusal telemetry confirmed). All
of runs 3/3c/4/5 trained from stock. Plausible cause: the selected llmfan46 26B-A4B
Heretic abliteration ships GGUF-only, so the bf16 safetensors pulled was stock.
This commit is contained in:
Vuong Hoang
2026-09-08 03:22:33 -07:00
parent f8a7985f02
commit 1282698e71
1 changed files with 13 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
persistent-memory.md
+13 -3
View File
@@ -131,9 +131,19 @@ COMPLETE and gated RESCUED (02:13 PDT). Live open items:_
(vllm-run05.pid), NO restart policy/systemd — does not survive a gx10 reboot; yields to the next training (vllm-run05.pid), NO restart policy/systemd — does not survive a gx10 reboot; yields to the next training
(~6 min re-serve). Brokkr: nothing further owed.** (~6 min re-serve). Brokkr: nothing further owed.**
- **run-4 gate = STILL-COUPLED** (RESULT-run04-gate.md, brokkr-smithy). Corpus dilution kept the - **run-4 gate = STILL-COUPLED** (RESULT-run04-gate.md, brokkr-smithy). Corpus dilution kept the
diversity gain, did NOT remove the safety/coherence regression. **Base-abliteration LABEL unresolved — diversity gain, did NOT remove the safety/coherence regression.
operator's ruling owed** (recipe says `-heretic`, provenance says stock; telemetry leans STOCK: base - **✅ RESOLVED (2026-09-08, settled from bytes): the R47 base is STOCK `google/gemma-4-26B-A4B-it`,
refused 77.7% hard, exact-repro of 3c). brokkr flags his lean as inference until the operator rules. byte-for-byte — NOT the abliteration.** The `-heretic-bf16` label in the recipes is a naming error;
run-04's "stock" provenance was right; brokkr's 77.7%-refusal telemetry lean is confirmed. Proof
(three-way match): local shards at `/home/infra-ops/models/gemma4-26b-a4b-it-bf16` sha256
`1127684971…`/`aab47033…` == the HF download etags (`.cache/huggingface/download/*.metadata`, so the
copy is uncorrupted) == the stock repo's two LFS oids, and the download commit `4d7ae498…` == stock
HEAD. Every run 3/3c/4/5 trained from a REFUSING stock base. Why plausible: the 2026-08-24 note
SELECTED llmfan46's Gemma-4-26B-A4B Heretic v1.2.0 ARA (3/100 refusals, bf16 51.6 GB), but llmfan46
ships that 26B-A4B abliteration **GGUF-only** — no bf16 safetensors — so the bf16 that actually got
pulled was stock google, and the `-heretic` name rode along from intent. **Operator/Brokkr decision
now evidenced (not a label guess): accept RESCUED-on-stock, or swap to a real abliteration (needs a
bf16 source, not the GGUF) + re-run. Recipes should drop `-heretic` from the base name.**
- **NASPool evac copy now safe to destroy** — scrub clean (0 err) AND PBS runs landing (verified 116 - **NASPool evac copy now safe to destroy** — scrub clean (0 err) AND PBS runs landing (verified 116
backups, 8 guests 09-06). `ospool/naspool-evac` (1.65T) can go once ONE Backrest run is confirmed: backups, 8 guests 09-06). `ospool/naspool-evac` (1.65T) can go once ONE Backrest run is confirmed:
`zfs destroy -r ospool/naspool-evac` + drop `@evac`. pfi-pve PSU1 dead + backplane bays 9/10 dead `zfs destroy -r ospool/naspool-evac` + drop `@evac`. pfi-pve PSU1 dead + backplane bays 9/10 dead