Richard Loyer 777c6979c1 eval: kit qualité A/B aveugle Qwen3.5-lmq4 vs dense (decode CPU, template, reasoning off) ... Bascule perf->qualité. Runner reproductible: genere un cahier de notation aveugle (out/results_blind.md) + cle (out/results_key.csv) sur 16 prompts FR (SUPPORT/SAFETY/ BOUNDARY/INSTRUCTION/GENERAL). Notation humaine, regle de decision dans PROTOCOLE. Resout l'eval shell (avant: template non applique -> ramble anglais): -cnv + -sysf + --reasoning off -> FR propre. out/ ignore (artefacts generes). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>		2026-05-26 22:24:23 +02:00
..
PROTOCOLE_QUALITE.md	eval: kit qualité A/B aveugle Qwen3.5-lmq4 vs dense (decode CPU, template, reasoning off)	2026-05-26 22:24:23 +02:00
prompts_fr.txt	eval: kit qualité A/B aveugle Qwen3.5-lmq4 vs dense (decode CPU, template, reasoning off)	2026-05-26 22:24:23 +02:00
run_quality_eval.sh	eval: kit qualité A/B aveugle Qwen3.5-lmq4 vs dense (decode CPU, template, reasoning off)	2026-05-26 22:24:23 +02:00
system_fr.txt	eval: kit qualité A/B aveugle Qwen3.5-lmq4 vs dense (decode CPU, template, reasoning off)	2026-05-26 22:24:23 +02:00