Add Wirkung organization card

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/banner.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,10 +1,47 @@
 ---
 title: README
-emoji: 💻
+emoji: 🔷
 colorFrom: gray
-colorTo: pink
+colorTo: blue
 sdk: static
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+![Wirkung compiles models, data, and computation into the shortest exact programs that produce them, and never computes the same thing twice.](./assets/banner.png)
+
+[Website](https://wirku.ng) · [Origami Family Paper](https://huggingface.co/wirkung/Origami-78B/blob/main/paper/Foss_2026_Origami_HCGM.pdf) · [Runtime (PyPI)](https://pypi.org/project/wirkung/) · [Prior Constant-State Releases](https://huggingface.co/tfwnotops) · [X (@FossDT)](https://x.com/FossDT) · [Contact](mailto:contact@wirku.ng)
+
+**Wirkung builds zero-retraining model compilers, lossless and spectral weight-folding formats, constant-memory ($O(1)$) attention carriers, and zero-VRAM disk-mapped inference runtimes across CPU, NPU, and GPU. Every system follows one decomposition, $X = X_{\mathrm{known}} + R$: keep what is known as an exact program and compute only the unseen remainder.**
+
+```bash
+pip install -U wirkung && wkng pull wirkung/Origami-9B -o ./Origami-9B && wkng verify ./Origami-9B
+```
+
+## Origami Model Family (Preview)
+
+Every Origami Preview model is compiled in closed form from its pretrained upstream checkpoint with **0 retraining steps**, **0 fine-tuning steps**, and **0 gradient updates**. Weights execute directly from SSD/NVMe storage via read-only OS `mmap` (`0 GB` GPU VRAM and `0 GB` dedicated weight-RAM required) with a strictly bounded $O(1)$ session state across arbitrary context lengths.
+
+| Repository | Architecture & Modality | Parameters | Source Checkpoint vs. Folded Bundle | Live Horizon State |
+|:--|:--|--:|:--|:--|
+| [`wirkung/Origami-78B`](https://huggingface.co/wirkung/Origami-78B) | Text & code MoE (`Aleph-Alpha/Kolibri-1`, 19,200 experts) | **78.10B** (3.46B active) | 156.21 GB BF16 → **26.42 GB** `.o1f1` (**5.91×**, SHA-256 lossless round-3) | **0.183 GB** constant $O(1)$ carrier |
+| [`wirkung/Origami-31B`](https://huggingface.co/wirkung/Origami-31B) | Multimodal dense (`google/gemma-4-31B-it`) | **32.68B** | 65.36 GB BF16 → **11.56 GB** `.o3f` (**5.65×**) | **0.036 GB** constant $O(1)$ carrier |
+| [`wirkung/Origami-27B`](https://huggingface.co/wirkung/Origami-27B) | Multimodal dense + rescued MTP (`Qwen/Qwen3.5-27B`) | **27.80B** | 55.60 GB BF16 → **7.44 GB** `.o3f` (**7.47×**) | **0.070 GB** constant $O(1)$ carrier |
+| [`wirkung/Origami-9B`](https://huggingface.co/wirkung/Origami-9B) | Multimodal GDN + attention (`Qwen/Qwen3.5-9B`) | **9.41B** | 18.82 GB BF16 → **2.74 GB** `.o3f` (**6.87×**) | **0.025 GB** constant $O(1)$ carrier |
+| [`wirkung/Origami-H3`](https://huggingface.co/wirkung/Origami-H3) | Video & multimodal MoE (`Lightricks/LTX-2.3` + `Gemma-3-12B`) | **21.60B** (3.60B active) | 46.12 GB BF16 → **10.38 GB** `.o3f` (**4.44×**) | **0.064 GB** constant spatiotemporal carrier |
+
+First-generation constant-state model releases compatible with standard `vLLM`, `MLX`, and `Transformers` stacks remain available under our sister organization [`huggingface.co/tfwnotops`](https://huggingface.co/tfwnotops).
+
+## Core systems
+
+- **Holographic Causal Graph Machine (`HCGM`) and `.o3f` / `.o1f1` folding.** Turns passive checkpoints into self-contained binary files on disk without retraining. Under the `v3-exakt` dyadic integer reduction contract, `AVX2`, `NEON`, general NPUs, `sGPU`, Apple Metal, and standalone driver-API PTX evaluate identical canonical reductions from a single artifact.
+- **`Wirkung` Engine.** Internal exact structural-law and closed-form operator synthesis engine used to derive constant-memory attention carriers (`ckv3`, zero-bit key-mean centering, exact doubly-stochastic and Sinkhorn attention surrogates) and compiled algebraic recurrences directly from empirical operators.
+- **Shared `M-Rail` (`.mrail` v3) and GPU-less server fleets.** Content-addressed associative trajectory manifold shared across processes or enterprise networks. Recurring workflows can be warmed up on one GPU (or a short cloud lease) and served permanently on disk-only CPU/NPU fleets; any unseen residual ($R \neq 0$) solved once by a single node is committed immediately for the entire fleet.
+- **Heavy Mixture of Experts (`HMoE`).** Deterministic routing across multiple disk-resident Origami models, static-graph NPU specialist pools, and sub-2 KB exact algebraic organs on a synchronous station bus (`cstar`) at zero idle weight-RAM cost.
+
+## Inquiries, custom compilation, and research collaboration
+
+We are available for custom zero-retraining model compilation (`HCGM` and `ConstantKV`), exact formula and algorithm synthesis via `Wirkung`, Shared `M-Rail` fleet licensing, enterprise partnerships, and research inquiries:
+
+- **Email:** [contact@wirku.ng](mailto:contact@wirku.ng)
+- **X:** [https://x.com/FossDT](https://x.com/FossDT)
+- **Website:** [https://wirku.ng](https://wirku.ng)