Vica Laya decision model
Vica Laya offers Korean text decisions through Q8 and Python checkpoints. Read its failed selection gates and limits of the consumed evaluation.
By tory-labs · 2026.11.08.1 trained release: 8 Nov 2026
A Korean-focused Laya multilingual fine-tune. Release 2026.11.08.1 continues from the previous original float checkpoint on private knowledge-graph and research summaries. It ships armD-final-epoch-3 as Q8_0 and original float weights. The maker records a release override with prior-task retention and news checks still unrun; it is not a selection-protocol pass.
Quick answers
What is Vica Laya by tory-labs?
Who makes Vica Laya?
Vica Laya: tory-labs
Standalone runtime bundles
The card now supplies vica-laya binaries with the same trained release. macOS uses Metal; Linux and Windows need a Vulkan loader. The x86_64 builds require AVX2, FMA and BMI2. The maker reports identical CPU and Metal answers after renaming GGUF metadata. This packaging change does not establish a new trained checkpoint or a new accuracy result.
Facts
- Inputs
- Text; Korean and English
- Licence
- Apache-2.0
- Access
- Self-contained macOS arm64, Linux x86_64 and Windows x86_64 runtime bundles; original float checkpoint for laya 0.4.22. The Laya GGUF is not an Ollama or llama.cpp chat-model package
Claims and sources
- The maker reports 155/178 calibration and 153/185 test summaries correct, versus 135/178 and 132/185 for the previous release. Labels come from two Opus 5.5 passes without human adjudication. Calibration selects the epoch and temperature; the test split compared all four experiment arms, so no independent final test is claimed. Existing news cohorts, judgment-retention tasks and warm-daemon latency were not measured for this release. vendor reportedsource
Links
Source: Model card and files →
Related projects
No related projects are listed in the registry.