▌system-one

~ / open-implementations / trained-replicas / frida-decisions

FRIDA-Decisions

SberAI's Russian-first encoder decision model: choice / score / noul plus a ranking question type, all questions scored in one packed encoder pass with an exact state cache. Torch, int8 ONNX, MLX, or vLLM.

section
Open Implementations
group
Trained replicas
source
github.com
repo
ai-forever/frida-decisions
stars
29 ▕████░░░░░░░░▏
7-day gain
+23
forks
2
language
Python
last pushed
oct 10
added to list
oct 12

## history

2026-09-270 → 29 stars2026-10-13

also in Trained replicas