Comparatif FR: 9B>4B (psy juste vs derive role), engine OK budget0

This commit is contained in:
Richard Loyer 2026-05-24 21:12:10 +02:00
parent 431865f07f
commit 9f7bc1e6c3
1 changed files with 3 additions and 0 deletions

View File

@ -93,3 +93,6 @@ Speaker 9B 5GB + Thinker Guard-4B 2.5GB = 7.5GB co-resident, 8GB libre. Guard-8B
## Fix moteur cascade: --reasoning-budget 0 (24/05) ## Fix moteur cascade: --reasoning-budget 0 (24/05)
BUG=enable_thinking default true -> /no_think ignore -> ramble anglais. FIX: --reasoning-budget 0 (arg.cpp:3061). Prouve: 4B->FR bref coherent "Je suis desole que tu te sens ainsi". Batch shell A/B reste impossible (HTP decode 0.6, EOS variable). Vrai cmp 4B vs 9B = JNI: decode CPU+template+budget0. Engine OK, cascade tient RAM. BUG=enable_thinking default true -> /no_think ignore -> ramble anglais. FIX: --reasoning-budget 0 (arg.cpp:3061). Prouve: 4B->FR bref coherent "Je suis desole que tu te sens ainsi". Batch shell A/B reste impossible (HTP decode 0.6, EOS variable). Vrai cmp 4B vs 9B = JNI: decode CPU+template+budget0. Engine OK, cascade tient RAM.
## Comparatif FR reel (budget0, HTP, pty) 24/05
9B>4B net: 9B posture psy juste+empathie; 4B inverse role/sentences generiques. Engine OK, FR coherent. Capture: adb direct=pty -> -st marche; script=pas tty. Reco 9B speaker. Thinker bullets + system bref a brancher pour cadrer. JNI = vrai pipeline.