cc-os/docs/memory-system/benchmark
jared 3e38398500 Complete graphify-ollama-setup OpenSpec change
Executes all 16 tasks: local extraction-model benchmark with qwen2.5-coder:7b
selected as the default (7B parameter count, multi-modal, outperforms Mistral on
structured output), disposable vault graph build workflow, and supporting docs.
Adds extraction model options handbook, updates implementation process with
reconciliation strategy, and archives the scoring results.
2026-06-05 11:44:40 -04:00
..
reference-outputs Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
dispatch-prompt.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
extraction-spec.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
local-llm-findings-2026-06-04.md Record post-reboot GPU timing and mark deferred #3 resolved 2026-06-04 14:52:21 -04:00
run-findings-2026-06-04.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
scoring-results-2026-06-04.md Complete graphify-ollama-setup OpenSpec change 2026-06-05 11:44:40 -04:00