Upload README.md with huggingface_hub

README.md

@@ -1,44 +1,82 @@
-# 🎯 Sentinel Quantization
+---
+tags:
+- sentinel-manifold
+- machine-learning
+- mathematical-foundations
+- quantization
+license: mit
+language:
+- en
+---
 
-## Overview
+# 🦴 Sentinel Quantization
 
-**Sentinel Quantization** — Model quantization using **dynamical constants** from the Sentinel function iteration.
+**Part of the Sentinel Manifold — One theorem, infinite applications.**
 
-## Key Innovation
+> `lim_{z→∞} F'(z)/F(z) = 1/e` — The Gradient Axiom
 
-Use proven dynamical properties of F(z) = Σ zⁿ/nⁿ as quantization parameters:
+---
 
-- **Zero-point**: C₁ = −0.007994021805953 (attracting fixed point)
-- **Scale factor**: 1/e = 0.367879441171442 (Gradient Axiom limit)
+## 📋 Description
 
-```python
-q = round((w - C₁) / (max|w| · 1/e))
-```
+4-8× model compression using dynamical constants. Zero-point Z = C₁ (attracting fixed point), scale S = max|w| · (1/e).
+
+---
 
-## Verified Results
+## 🧠 Mathematical Foundation
 
-| Property | Standard INT8 | Sentinel INT8 |
-|----------|--------------|--------------|
-| Zero-point | Manual (0 or learned) | **C₁ = −0.007994…** |
-| Scale | Empirical (max/255) | **max·(1/e)** |
-| Theoretical basis | None | **Dynamical constants** |
-| Compression | 4.0× | **4.0×** |
-| Dequantization error | ~0.01 | **0.0044** |
+### Core Constants
+| Constant | Value | Role |
+|----------|-------|------|
+| C₁ (Attractor) | -0.007994021805953 | Zero-point / quantization |
+| C₂ (Tripwire) | 0.000200056042968 | Security / curriculum |
+| 1/e (Axiom) | 0.367879441171442 | Gradient scaling limit |
 
-## Code
+### Theorem
+```
+F(z) = Σ zⁿ/nⁿ   (Sophomore's Dream, Bernoulli 1697)
+lim_{z→∞} F'(z)/F(z) = 1/e ≈ 0.367879441171442
+```
 
-See `sentinel_quantization.py` for:
-- `SentinelQuantizer`
-- `SentinelQuantizedLinear`
-- `demo_sentinel_quantization()` (synthetic model)
+---
 
-## Repository
+## 🏆 Verified Results
 
-[5dimension/sentinel-quantization](https://huggingface.co/5dimension/sentinel-quantization)
+| Format | Compression | Zero-Point |
+|--------|-------------|------------|
+| FP32 | 1× | — |
+| Sentinel-INT8 | 4× | Z = C₁ |
+| Sentinel-INT4 | 8× | Z = C₁ |
 
-## Applications
+---
+
+## 🎯 Use Cases
 
 - Edge deployment (mobile, IoT)
 - Real-time inference
-- Memory-constrained environments
-- Model compression for LLMs
+- Microcontroller deployment
+
+---
+
+## 🔗 Links
+
+- **Main repo**: [sentinel-manifold-discoveries](https://huggingface.co/5dimension/sentinel-manifold-discoveries)
+- **All algorithms**: [5dimension](https://huggingface.co/5dimension)
+- **Interactive Space**: [sentinel-hub](https://huggingface.co/spaces/5dimension/sentinel-hub)
+
+---
+
+## 📚 Citation
+
+```bibtex
+@misc{abdel-aal2026sentinel,
+  title={The Sentinel Manifold: A Unified Mathematical Framework for Machine Learning},
+  author={Abdel-Aal, Romain},
+  year={2026},
+  url={https://huggingface.co/5dimension/sentinel-manifold-discoveries}
+}
+```
+
+---
+
+**License:** MIT | **One theorem, infinite models.** 🦴