Qovaryx 3B scratch base
Random-initialized weights. Training is required before this artifact can perform a useful language or classification task. The size in the repository name is a family label; it is not a benchmark result.
Status — October 3, 2026: Qovaryx is on the back burner. Desktop downloads are paused; there is no current public installer, purchase, or trial. These repositories remain as research references. Published weights are separate from desktop product availability.
Configuration
| Field | Published value |
|---|---|
| Architecture | FinanceDecoder |
| Width | 2944 |
| Decoder layers | 32 |
| Attention heads | 16 |
| Feed-forward width | 7680 |
| Vocabulary size | 32,000 |
| Configured maximum sequence length | 4,096 |
These values come from config.json. They describe the supplied configuration, not measured training throughput, hardware compatibility, or model capability. Optional architecture mechanisms require compatible code, configuration, and training; their presence does not establish learned performance.
Repository format
This release contains pytorch_model.pt, config.json, and tokenizer.json. The configuration records random initialization with seed 17. It uses the custom FinanceDecoder format, with a 32,000-token vocabulary.
The historical loading path requires compatible FinanceDecoder and DecoderConfig classes from bleeding_edge.model.decoder, which are not bundled here. This release does not contain the Transformers wrapper files supplied in the three smaller scratch-base repositories. Obtain and inspect compatible source before loading; the compiled Q-Office-Suite binary does not supply that Python source package.
Evaluation and lineage
No task-performance result is claimed for these random weights. Results from separately trained specialist or Cluster Shell experiments cannot be attributed to this untrained checkpoint. Historical claims about frontier-level cognition, general hardware fit, or the quality of optional backends have been removed.
The trained Q-* specialist releases are separate checkpoints with their own configurations, tokenizers, dependencies, and evaluation limits. A scratch-base repository is not evidence that a particular specialist was trained directly from these exact uploaded weights.
License
Apache-2.0, as recorded in the existing model metadata. Review the supplied code and any third-party training data or dependencies separately.
Project and support
J.E. Herizon LLC, doing business as JE Horizon.