docs: Jev candidate bench vs SemIf (fv-ml1 GPU 3) — Intern-Decision-4B is the replacement if SemIf is displaced

Operator ask relayed by brokkr-smithy-dev. Positive control (SemIf 187/231, hard 0.613) reproduced exactly; negative control and a 4-restart noise floor (0 flips) measured. On our replaced-baseline sets no candidate beats SemIf-with- rotations beyond the ~4-pt floor; Intern-Decision-4B native matches it at one ordering, is better on Wyrd, fits 9.7/10.3 GB and is 1.5-2.3x faster. JevBench rank does not transfer. Raw per-item data kept out of git.
2026-09-30 05:00:45 -07:00
parent 9a6ac59da7
commit 475d6d6bcb
27 changed files with 19068 additions and 0 deletions
@@ -0,0 +1,6 @@
+{
+  "repo": "Qwen/Qwen3.5-4B",
+  "revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
+  "path": "/hf/hub/models--Qwen--Qwen3.5-4B/snapshots/851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
+  "note": "Jev bench 2026-09-30: imajev's own pinned base (artifacts/model-qwen4b.json), pointed at fv-ml1's HF cache"
+}