2.1 KiB
2.1 KiB
[2026-09-08] R47 base provenance SETTLED from bytes — it is STOCK, not heretic
Operator-directed question (relayed via brokkr): which weights are at
/home/infra-ops/models/gemma4-26b-a4b-it-bf16 — stock instruct or the heretic
abliteration? Two labels disagreed (recipes say -heretic-bf16; run-04
provenance says stock) on ONE path with no model card. Settle from bytes.
Answer: STOCK google/gemma-4-26B-A4B-it, byte-for-byte.
Three-way match, zero ambiguity:
- Local shards (sha256 on gx10):
model-00001=1127684971bbca40465435a5cad69d67ad603bf5e61c6dfd5561fae4a3bcfdb3,model-00002=aab47033e1e8a492ef8e581efae1cf36478d0433567e7729b3c1728bc8970db7. Both equal the HF download etags in.cache/huggingface/download/*.metadata→ the local copy is uncorrupted, exactly what was pulled. - Download commit in that same metadata:
4d7ae4984b7db7de8f8457170b3f1a419ee76d52. - HF
google/gemma-4-26B-A4B-it(gated:false, queried with the localhf_HBlJ…token in~/.config/secrets/env.sh): HEAD sha ==4d7ae498…, and its two safetensors LFS oids are1127684971…/aab47033…— identical to (1).
Commit + both shard hashes match at the stock repo's current HEAD. Behavioral corroboration: the base hard-refuses ~77.7% (brokkr's k=25) = stock, not a 3/100-refusal abliteration.
What it means
- The recipes'
-heretic-bf16label is a naming error; run-04's "stock" provenance was right. Every run 3/3c/4/5 trained from a refusing STOCK base. - Why plausible: the 2026-08-24 trainee-selection 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 got
pulled was stock google and the
-hereticname rode along from intent. - Brokkr took the corrections his side (drop
-hereticfrom the run-5 emitter + docs, annotate run-4's recipe, fix the 2026-08-24 note). The accept-vs-swap choice is the operator's, now evidenced — see 2026-09-08-run5-rescued.
Commit: 1282698. Thread: althing 01M207X7SKY2ZDKYREBAQ17CE1.