Jevora 9B decision model

Jevora 9B returns choices and probabilities through a custom loader. Read its pinned V1.6 package, public-suite coverage and calibration limits.

By kadirbekovvv / doxanocap · Pinned V1.6 package at 06:55 UTC; catch-up verification: 8 Nov 2026

A Qwen3.5-9B LoRA decision model with a separate 255-option head. The pinned V1.6 package returns one zero-based choice and ordered probabilities through POST /decision. It needs the public custom loader; it does not generate explanations or tool calls. The package predates this scan window, while the availability clarification appeared during it.

Quick answers

Facts

Base

Post-trained Qwen/Qwen3.5-9B; rank-64 LoRA and a separate BF16 decision head

Inputs

Text context and 2 to 255 ordered, non-empty options

Limits

8,192 rendered tokens; no silent truncation

Licence

Apache-2.0 project code and derivative weights; upstream components and datasets retain their terms

Access

Pinned complete V1.6 package at revision 545549b8e8104f1780966ef1c13136abb32712b4; custom Python 3.13 loader

Claims and sources

• The maker reports public Decision Index 0.3 skill 49.83 and balanced raw score 62.28: 140,299 of 140,620 requests answered, with 321 unsupported and no errors. Development data selected update 71,327, so its 254/352 result is not an independent final test. V1.6 uses temperature 1 without fitted calibration. No private Full score or official rank is asserted. vendor reportedsource
• The card reports operator-run tensor parity and three cold CUDA research/public-loader checks with zero maximum probability difference. This scan checks the pinned file inventory, manifest hashes and checkpoint metadata; it does not repeat GPU inference or verify an independently published parity receipt. vendor reportedsource

Links

Source: Current V1.6 card → Source: Pinned package → Source: Loader and licence → Source: Package manifest →

Related projects

No related projects are listed in the registry.

All projects · Back to the model registry