Blame for README.md

---
title: Osakra Research
colorFrom: blue
colorTo: indigo
sdk: static
pinned: false
---

<div align="center">

<img src="https://huggingface.co/spaces/Osakra/README/resolve/main/osakra_research_logo.png" width="380" alt="Osakra Research Logo" />

# Osakra Research
**Independent Computational Cognition, Continuous Dynamics & Relational Neuro-Symbolic Architectures**

[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
[![Compute Target](https://img.shields.io/badge/Compute-Consumer%20Hardware%20%28%3C%205.8%20GB%20VRAM%29-informational.svg)](https://huggingface.co/Osakra)
[![Architecture](https://img.shields.io/badge/Architecture-N.O.R.N.%20Framework-00c980.svg)](https://huggingface.co/Osakra)
[![Evaluation Suite](https://img.shields.io/badge/Benchmark%20Suite-1%2C250%20Tasks%20Bundled-orange.svg)](https://huggingface.co/Osakra)

</div>

---

### About Osakra Research

Osakra Research is an independent computational research effort exploring continuous-time dynamical systems, latent representation manifolds, and vector-symbolic architectures in compact language models.

Rather than scaling parameter counts across massive distributed clusters, this project investigates targeted architectural questions under strict consumer hardware constraints (< 5.8 GB active VRAM on a single consumer GPU): can compact open backbones deliberate directly within continuous hidden vector manifolds (h ∈ ℝᵈ) and maintain algebraic invariants without relying solely on verbose textual token emission?

This line of inquiry forms the basis of the **N.O.R.N.** architecture (**N**euro-symbolic **O**DE & **R**elational **N**etworks), a dual-tier framework pairing discrete autoregressive deliberation with continuous associative memory engines.

---

### Core Research Areas

* **Relational Graph Holographic Reduced Representations (HRR):**
  Binding topological graphs, causal transition triples, and algebraic structures directly in a 1024-dimensional continuous vector space using complex Fourier-domain circular convolutions `F⁻¹(F(a) ⊙ F(b))`, mitigating representation drift and attention dispersal across long-horizon deduction.

* **Continuous-Time Dynamical Modulation (LTC-ODEs):**
  Utilizing Liquid Time-Constant (LTC) ordinary differential equations and leaky integrators to govern continuous latent state evolution between discrete token transitions.

* **Deterministic Agentic Tool Evaluation:**
  Auditing model capabilities on live subprocess code execution (the 250-task Agentic Sandbox) to differentiate genuine, typed, modular software engineering from fragile single-line scripting shortcuts that collapse on complex algorithms.

* **Weight-Space Consolidation & Inference Efficiency:**
  Investigating the mechanics of fused adapter checkpoints to understand why consolidated parameter representations yield sub-second inference speeds (0.38s/task) compared to unmerged deliberation paths.

---

### Releases & Research Checkpoints

* **[Project Norn V18 (9B Hybrid HRR)](https://huggingface.co/TheEpiales/Project-Norn-V18-9B):**
  Our 9B hybrid reasoning checkpoint quantized to Q4_K_M GGUF (< 5.8 GB VRAM, 100% local GPU offload). Integrates a native 4096-dimensional hidden projection, a 1024-dimensional 4-channel Relational Graph HRR engine (`norn_biology_proj_v18.pt`), and evaluation against our bundled 1,250-benchmark multi-pillar suite (81.8% Micro / 80.6% Macro accuracy; 94.0% live agentic tool accuracy).

* **[Project Norn V17 (4.5B Standalone Merged Dual-Tier)](https://huggingface.co/TheEpiales/Project-Norn-V17-4.5B):**
  A consolidated 4.5B parameter dual-tier cognitive system. Bundles complete FP16 safetensors, 4-bit GGUF, and original LoRA adapter weights, demonstrating ultra-fast 0.38s/task agentic tool execution.

* **[Project Norn V15 (4.45B Auto-Router Prototype)](https://huggingface.co/Osakra/norn-v15):**
  The foundational proof-of-concept testing continuous latent Chain-of-Thought recurrence (k ∈ [2, 16]) and associative memory seeding on top of a 4-bit quantized base.

---

### Grounded Scope & Reproducibility

* **Single-Author Research:** This is focused, exploratory academic research. These models are designed to probe continuous representations, invariant tracking, and compact reasoning, and do not compete with 70B+ proprietary models on open-domain trivia or massive encyclopedic memorization.
* **Full Community Replication:** Every release bundles raw evaluation suites, deterministic scoring harnesses, audit runners, and transparent execution traces directly in the repository under the Apache-2.0 license to facilitate independent community replication and mechanistic interpretability analysis.