README / README.md
goautomate-ai's picture
Update README.md
a707198 verified
|
Raw
History Blame Contribute Delete
9.42 kB
<div align="center">
<img src="https://www.goautomate.institute/logo1.png" alt="GoAutomate AI Institute" width="90" />
<h1>GoAutomate AI Institute</h1>
<h3>Canadian Sovereign AI, built for public benefit 🍁</h3>
**Accessible · Responsible · Canadian‑governed**
![Canadian Sovereign AI](https://img.shields.io/badge/Canadian-Sovereign_AI-2f80ed?style=flat-square)
![Structure](https://img.shields.io/badge/Structure-Not--for--profit-4fd1c5?style=flat-square)
![Models](https://img.shields.io/badge/Models-Open_Weights-1f6feb?style=flat-square)
![Focus](https://img.shields.io/badge/Focus-Ternary_1.58--bit-07111f?style=flat-square)
[![Website](https://img.shields.io/badge/Website-goautomate.institute-2f80ed?style=for-the-badge&logo=googlechrome&logoColor=white)](https://www.goautomate.institute)
[![Paper](https://img.shields.io/badge/Paper-TR--2026--001-1f6feb?style=for-the-badge&logo=zenodo&logoColor=white)](https://doi.org/10.5281/zenodo.21110909)
[![Contact](https://img.shields.io/badge/Contact-info@goautomate.ai-16a34a?style=for-the-badge&logo=gmail&logoColor=white)](mailto:info@goautomate.ai)
<em>Advancing efficient, sovereign artificial intelligence for Canada — and sharing the methods with the world.</em>
</div>
---
## 🏛️ Who we are
The **GoAutomate AI Institute** is a not‑for‑profit advancing **Canadian sovereign artificial intelligence** — AI models, tools, and research designed for Canadian organizations and aligned with Canadian values, ethics, and governance.
We don't believe Canada has to win only the race toward ever‑larger frontier models. **Purpose‑built, efficient, Canadian‑governed models** can deliver real outcomes in real environments — hospitals, health authorities, public institutions, businesses, researchers, and not‑for‑profits — while keeping people in control and accountable.
This organization is where we publish our **open‑weight models, inference research, and technical reports.**
### At a glance
| | |
|---|---|
| **Mission** | Canadian sovereign AI, for public benefit |
| **Model family** | **Terna** — ternary‑weight models (*Latin* terni, "three each") |
| **First release** | **Terna‑E2B** — ternary distillation of Gemma‑4‑E2B *(pre‑release)* |
| **Format** | GGUF · runs on `llama.cpp` |
| **Flagship report** | TR‑2026‑001 · [DOI 10.5281/zenodo.21110909](https://doi.org/10.5281/zenodo.21110909) |
| **Structure** | Not‑for‑profit · open weights |
---
## 🔬 Our research bet: ternary
Modern AI isn't limited by intelligence — it's limited by **the cost of storing and moving it**. Most of the cost of running a language model is the memory bandwidth spent streaming billions of weights for every token, and the arithmetic of multiplying them.
**Ternary** representation constrains every weight to one of three values — **{ −1, 0, +1 }** — and attacks both costs at once:
| ≈ 8–10× smaller | Multiply‑free | Capability preserved |
|:---|:---|:---|
| Each weight carries ≈ **1.58 bits** (log₂3) instead of 16 — roughly an order of magnitude below half precision, and about half the size of 4‑bit quantization. | A weight in { −1, 0, +1 } turns the expensive multiply into **add**, **subtract**, or **skip**. Roughly a third of the work disappears as structured sparsity. | Reached through **distillation** — a ternary student trained to reproduce a high‑precision teacher, so the constraint is *learned*, not imposed after the fact. *Subtract cost, not intelligence.* |
The payoff spans hardware generations: ternary's footprint lets capable models **fit on memory‑constrained edge devices** and **revive legacy datacenter GPUs** that modern models had outgrown — extending the useful life of existing silicon — while on modern accelerators the same savings mean **far more concurrent users per device**. It's an environmental story as much as a performance one: less energy per token, fewer accelerators per unit of served intelligence, and a slower path to e‑waste.
---
## ⭐ Featured release — Terna‑E2B
![status](https://img.shields.io/badge/status-pre--release-f59e0b?style=flat-square)
![format](https://img.shields.io/badge/format-GGUF-1f6feb?style=flat-square)
![base](https://img.shields.io/badge/base-Gemma--4--E2B-2f80ed?style=flat-square)
[![license](https://img.shields.io/badge/license-Gemma-4fd1c5?style=flat-square)](https://ai.google.dev/gemma/terms)
**Terna‑E2B** is our first release, and the first in the **Terna** family of ternary‑weight models (*Terna*, from Latin *terni*, "three each"). It is a ternary (≈1.6‑bit) distillation of **Gemma‑4‑E2B**, a capability‑dense model with a **transparent, Western open‑weight lineage**, distributed as **GGUF** for efficient local and datacenter serving.
> ⚠️ **Pre‑release checkpoint.** The published weights are an early checkpoint (~1B training tokens), shared to demonstrate the method and invite community evaluation. **Production weights (~15B tokens) with full capability benchmarks will follow and replace them.** We defer quantitative capability claims to that release rather than over‑state a pre‑release checkpoint.
*Browse the model repositories in this organization for files, quantizations, and usage.*
---
## 🎯 Why Gemma‑4 as the base
- **Exceptional intelligence‑per‑FLOP.** An already capability‑dense family; ternary distillation compounds that efficiency.
- **Elastic architecture.** The E2B ("effective‑2B") design fits edge and multi‑tier deployment — and ternary lowers the floor of that range further.
- **Provenance you can defend.** For regulated and sovereignty‑sensitive sectors — healthcare, public sector, critical infrastructure — the *provenance* of a model's knowledge is a governance requirement, not a preference. A transparent, auditable, Western open‑weight base gives the resulting ternary model a clear, documentable lineage. **Efficiency should not come at the cost of provenance.**
---
## ⚙️ An engine built to spend ternary's footprint on throughput
Ternary's memory savings are only as valuable as a serving stack's ability to convert them into useful work. We maintain an inference engine (a fork of the open‑source `llama.cpp` lineage) tuned so footprint becomes **concurrency and throughput**:
- **Footprint → concurrent contexts** — small weights leave far more device memory for KV cache, so one accelerator serves many more simultaneous sessions.
- **Hardware‑best matmul dispatch** — the engine picks the path that fits the device by batch size, so capability‑dense models serve efficiently even on GPUs that lack dedicated matrix‑multiply units.
- **Device‑side sampling** and **shared‑prefix / cross‑session cache reuse** — agentic workloads pay for a large shared system prompt once, not once per user.
We validate this across **deliberately different accelerator families** — legacy datacenter GPUs and earlier‑generation tensor‑core GPUs — to prove the ternary‑plus‑engine approach spans hardware generations. Every serving optimization is held to a **token‑identical correctness gate** before it ships: throughput work never silently degrades output.
---
## 📄 Research
[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.21110909.svg)](https://doi.org/10.5281/zenodo.21110909)
- **[TR‑2026‑001 — *Ternary Foundations for Efficient, Sovereign AI*](https://doi.org/10.5281/zenodo.21110909)** — the mathematics of ternary, why Gemma‑4, the engine that turns footprint into throughput, and the implications for legacy and modern hardware. *(Zenodo · CC‑BY‑4.0)*
- **TR‑2026‑002 — *Quantization‑Aware Training and Ternary Weights: Method vs. Representation*** — clears the "QAT vs ternary" category error and places both on one efficiency curve.
Further reports — on serving engines across accelerator families, multi‑GPU parallelism for heterogeneous fleets, shared‑context concurrency, ternary at larger scales, and governable agentic orchestration — are on the Institute's roadmap.
---
## 🤝 What we stand for
| | |
|---|---|
| 🍁 **Sovereignty** | Reduce dependency on foreign‑controlled AI models and infrastructure; support Canadian laws, governance, and interests. |
| 🛡️ **Responsibility** | Steerable, explainable, accountable, secure systems that keep humans at the helm. |
| 🌐 **Accessibility** | Capable models, tools, and documentation available to organizations across Canada. |
| ⚡ **Efficiency** | Capability that scales **down** in cost as readily as it scales up in ability. |
---
## 📬 Get involved
The GoAutomate AI Institute welcomes collaboration with **Canadian organizations, healthcare systems, public institutions, researchers, policymakers, and technology leaders** who share our commitment to responsible and accessible AI.
<div align="center">
[![Website](https://img.shields.io/badge/Website-goautomate.institute-2f80ed?style=for-the-badge&logo=googlechrome&logoColor=white)](https://www.goautomate.institute)
[![Collaborate](https://img.shields.io/badge/Collaborate-info@goautomate.ai-16a34a?style=for-the-badge&logo=gmail&logoColor=white)](mailto:info@goautomate.ai)
</div>
---
<div align="center">
<sub>© 2026 GoAutomate AI Institute · Canadian Sovereign AI · Responsible Adoption · Public Benefit</sub>
</div>