Instructions to use geraldaton20/hd-laya with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Laya
How to use geraldaton20/hd-laya with Laya:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
hd-laya
hd-laya is a neuro-symbolic decision model built on top of the pure, un-distilled upstream laya System-1 engine. It removes laya's ~20-option choice ceiling and lets a hyperdimensional (HDC/VSA) workspace manage context.
- v0.1 (GitHub): no-train HDC harness around unmodified laya checkpoints.
- v1.0 (this release): trained components β HDC option slots, HDC-context hypertoken projection, realtime RLCD refine loop.
Measured laws (probes 1β5)
| Probe | Verdict |
|---|---|
| 1 speed | scan sweet spot 1024β2048d |
| 2 matryoshka | two-stage == full-D (0β0.056%); β€2.8Γ scan speedup |
| 3 semantic | 512-bit SimHash β float top-1 within near-ties; β₯2048 exact |
| 4 capacity | D/64 pairs exact-or-refuse |
| 5 head update | realtime RLCD: 23β63 ms/update on T4 |
Artifacts
hd_laya_head.ptβ trained head checkpoint (PyTorch state_dict, 1000 steps, K=[77,150])head.onnxβ promoted head in ONNX (opset 17, verified on ONNX Runtime CPU)
Inference
ONNX Runtime (CPU/CUDA) + PyTorch/transformers. Encoder is a frozen graph; the head is swappable (promote-on-gate).
License
Apache-2.0 (derived from laya; attribution to NandhaKishorM/laya).
Links
- GitHub: https://github.com/sensesVoid/hd-laya
- SQAC docs: design spec + probe verdicts (project key
hd-laya)
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support