noonghunnaandClaude Opus 4.8 8b3aa13f54 docs(vibethinker-3b): add measured one-shot-coding scores (HE+ 97%, LCB 83%) ...

Code packs run 2026-06-16 (tool-free — sandbox executes the model's code, no
tool-calls): humaneval-plus-30 29/30 (97%), lcb-v6-30 25/30 (83%, 2 losses =
token_limit on the hardest). Substantiates the 'strong one-shot/competition
coding' characterization with our own numbers (matches the authors' ~96% LeetCode).
Folded into the llamacpp compose Quality field + registry status_note.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>

2026-06-16 21:08:40 +00:00

..

profiles

docs(vibethinker-3b): add measured one-shot-coding scores (HE+ 97%, LCB 83%)

2026-06-16 21:08:40 +00:00

bench-row-formatter.sh

refactor(launch): derive launcher tables from the registry + <engine>/default resolver

2026-05-26 18:35:35 +00:00

compose-meta.sh

chore(254): archive 15 Genesis/nightly composes + migrate the cascade [WIP: 5 test fixtures]

2026-06-05 13:37:48 +00:00

generate_compose.py

refactor(vllm): reconcile vLLM engines to v0.22.0 — two-engine split (#254)

2026-06-05 11:27:17 +00:00

owui-register.sh

switch.sh --owui: auto-register a launched model in Open WebUI

2026-06-10 00:07:19 +00:00

registry-emit.sh

Operational robustness (#281): orphan-safe switch.sh · reboot-surviving vLLM · multi-GPU power sweep (#285)

2026-05-31 22:13:52 +05:00

report_calib.sh

fix(#168): scope report.sh kv-calc calibration to the running model

2026-05-23 22:19:37 +00:00