▌system-one

~ / open-implementations / trained-replicas / jiwo

jiwo

Small trained decision models on Qwen3.5 (0.8B and 4B) serving /v1/systemone at ~50 ms on one H100. jiwo-0.8b ranks #1 of 27 under 1B on the Decision Index board; both models are on the board. Apache 2.0.

section
Open Implementations
group
Trained replicas
source
github.com
repo
jiwidi/jiwo
stars
106 ▕█████░░░░░░░▏
7-day gain
+106
forks
0
language
Python
license
MIT
last pushed
oct 10
added to list
oct 12

## history

2026-10-040 → 106 stars2026-10-13

also in Trained replicas