Commit Graph

4 Commits

Author SHA1 Message Date
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
Richard Loyer b2fc564f04 Engine sur fork qualcomm: decode dense 15.5>pte, 3.5 ~11, KVq8+t4+fa+lm_head-Q4; prefill 93/285; RAG cross 24-28k
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 15:53:14 +02:00
Richard Loyer 7dbf38db97 Doc complete: README+MODELS+PERF+PITFALLS, build nettoye 2026-05-24 21:59:56 +02:00
Richard Loyer cc5b033762 Engine cadrage: CLAUDE.md analyse R&D, verdict NPU-prefill/CPU-decode
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 12:34:14 +02:00