# Jevora 9B decision model by kadirbekovvv / doxanocap

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

Updated 2026-11-12 (Australia/Adelaide)

## Quick answers

### What is Jevora 9B by kadirbekovvv / doxanocap?

[Jevora 9B](<https://decisionmodels.ai/models/jevora>): A Qwen3.5-9B LoRA decision model with a separate 255-option head.

[Jevora 9B facts](<https://decisionmodels.ai/models/jevora>)

[Source](<https://huggingface.co/kadirbekovvv/jevora-9b-v1>)

### Who makes Jevora 9B?

[Jevora 9B](<https://decisionmodels.ai/models/jevora>): kadirbekovvv / doxanocap

[Jevora 9B facts](<https://decisionmodels.ai/models/jevora>)

[Source](<https://huggingface.co/kadirbekovvv/jevora-9b-v1>)

By kadirbekovvv / doxanocap · Pinned V1.6 package at 06:55 UTC; catch-up verification: 2026-11-08 · OPEN

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.

## 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

- **VENDOR-REPORTED**: 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. [source](<https://huggingface.co/kadirbekovvv/jevora-9b-v1>)
- **VENDOR-REPORTED**: 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. [source](<https://huggingface.co/kadirbekovvv/jevora-9b-v1>)

## Links

- [Source: Current V1.6 card](<https://huggingface.co/kadirbekovvv/jevora-9b-v1>)
- [Source: Pinned package](<https://huggingface.co/kadirbekovvv/jevora-9b-v1/tree/545549b8e8104f1780966ef1c13136abb32712b4>)
- [Source: Loader and licence](<https://github.com/doxanocap/jevora-9b-v1>)
- [Source: Package manifest](<https://huggingface.co/kadirbekovvv/jevora-9b-v1/blob/545549b8e8104f1780966ef1c13136abb32712b4/jevora-9b-v1/manifest.json>)

## Related projects

No related projects are listed in the registry.