Instructions to use GoAutomateAI/terna-e2b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GoAutomateAI/terna-e2b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GoAutomateAI/terna-e2b-GGUF",
	filename="terna-e2b-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use GoAutomateAI/terna-e2b-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GoAutomateAI/terna-e2b-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf GoAutomateAI/terna-e2b-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GoAutomateAI/terna-e2b-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf GoAutomateAI/terna-e2b-GGUF:Q2_K

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf GoAutomateAI/terna-e2b-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf GoAutomateAI/terna-e2b-GGUF:Q2_K

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf GoAutomateAI/terna-e2b-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GoAutomateAI/terna-e2b-GGUF:Q2_K

Use Docker

docker model run hf.co/GoAutomateAI/terna-e2b-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use GoAutomateAI/terna-e2b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GoAutomateAI/terna-e2b-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GoAutomateAI/terna-e2b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GoAutomateAI/terna-e2b-GGUF:Q2_K

Ollama
How to use GoAutomateAI/terna-e2b-GGUF with Ollama:
```
ollama run hf.co/GoAutomateAI/terna-e2b-GGUF:Q2_K
```

Unsloth Studio

How to use GoAutomateAI/terna-e2b-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for GoAutomateAI/terna-e2b-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for GoAutomateAI/terna-e2b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GoAutomateAI/terna-e2b-GGUF to start chatting

How to use GoAutomateAI/terna-e2b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GoAutomateAI/terna-e2b-GGUF:Q2_K

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "GoAutomateAI/terna-e2b-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use GoAutomateAI/terna-e2b-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GoAutomateAI/terna-e2b-GGUF:Q2_K

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default GoAutomateAI/terna-e2b-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use GoAutomateAI/terna-e2b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GoAutomateAI/terna-e2b-GGUF:Q2_K

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "GoAutomateAI/terna-e2b-GGUF:Q2_K" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use GoAutomateAI/terna-e2b-GGUF with Docker Model Runner:
```
docker model run hf.co/GoAutomateAI/terna-e2b-GGUF:Q2_K
```

Lemonade

How to use GoAutomateAI/terna-e2b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GoAutomateAI/terna-e2b-GGUF:Q2_K

Run and chat with the model

lemonade run user.terna-e2b-GGUF-Q2_K

List all available models

lemonade list

terna-e2b-GGUF / README.md

goautomate-ai

Update README.md

7f57d47 verified 6 days ago

preview code

Raw

History Blame Contribute Delete

9.3 kB

	---
	license: gemma
	license_link: https://ai.google.dev/gemma/terms
	base_model: google/gemma-4-E2B-it
	base_model_relation: quantized
	language:
	- en
	pipeline_tag: text-generation
	library_name: gguf
	tags:
	- gguf
	- ternary
	- bitnet
	- 1.58-bit
	- gemma
	- gemma-4
	- quantization-aware-training
	- distillation
	- sovereign-ai
	- edge
	- efficient-inference
	- llama.cpp
	---

	<div align="center">

	<img src="https://www.goautomate.institute/logo1.png" alt="GoAutomate AI Institute" width="90" />

	<h1>Terna‑E2B (GGUF)</h1>

	<h3>A ternary (~1.6‑bit) distillation of Gemma‑4‑E2B · <b>Pre‑release</b> 🍁</h3>

	GoAutomate AI Institute — Canadian Sovereign AI

	![status](https://img.shields.io/badge/status-pre--release-f59e0b?style=flat-square)
	![format](https://img.shields.io/badge/format-GGUF_Q2__K-1f6feb?style=flat-square)
	![base](https://img.shields.io/badge/base-Gemma--4--E2B-2f80ed?style=flat-square)
	![weights](https://img.shields.io/badge/weights-~1.58--bit_ternary-07111f?style=flat-square)
	[![license](https://img.shields.io/badge/license-Gemma-4fd1c5?style=flat-square)](https://ai.google.dev/gemma/terms)

	[![Organization](https://img.shields.io/badge/Organization-GoAutomateAI-ffcc4d?style=for-the-badge&logo=huggingface&logoColor=white)](https://huggingface.co/GoAutomateAI)
	[![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)

	</div>

	---

	Terna is the GoAutomate AI Institute's family of ternary‑weight language models. The name comes from the Latin terni — "three each" — a nod to the three values every weight is constrained to: { −1, 0, +1 }, the ternary representation at the heart of the family. That constraint is our defining bet: models that are ≈8–10× smaller and multiply‑free, engineered to subtract cost, not intelligence — capable from the edge to legacy datacenter GPUs to modern accelerators. Terna‑E2B is the first member of the family.

	---

	> ## ⚠️ Pre‑release checkpoint — read first
	> These weights are an early checkpoint trained on ~1B tokens, published to demonstrate the method and invite community evaluation. They are not a finished model. Expect fluent‑but‑confidently‑wrong answers, and verify every output. Production weights (~15B tokens) with full capability benchmarks will follow and replace this checkpoint. We deliberately defer quantitative capability claims to that release.

	---

	## Model at a glance

	\| \| \|
	\|---\|---\|
	\| Base / teacher \| [`google/gemma-4-E2B-it`](https://ai.google.dev/gemma) (capability‑dense, Western open‑weight lineage) \|
	\| Method \| Quantization‑aware distillation to ternary weights — learned, not post‑hoc rounded \|
	\| Weight representation \| Ternary — each weight ∈ { −1, 0, +1 } (≈1.58 bits; ≈8–10× smaller than FP16, ≈2× smaller than 4‑bit) \|
	\| Format \| GGUF (`Q2_K`), runs on llama.cpp \|
	\| Language \| English \|
	\| Training tokens (this release) \| ~1B (pre‑release checkpoint) \|
	\| License \| [Gemma Terms of Use](https://ai.google.dev/gemma/terms) \|

	---

	## What is ternary?

	Ternary constrains every weight to one of three values — { −1, 0, +1 } — which does two things at once:

	- Footprint collapses to ≈1.58 bits per weight (log₂3), roughly an order of magnitude below half precision.
	- The multiply disappears: `w · x` with `w ∈ {−1, 0, +1}` is just add x, subtract x, or skip — a general matrix‑multiply becomes a sparse signed sum, with ~⅓ of the work vanishing as structured sparsity.

	Crucially, we reach ternary through distillation — training a ternary "student" to reproduce a high‑precision Gemma‑4‑E2B "teacher" — so the constraint is learned, not crudely imposed on a finished model. The guiding principle: subtract cost, not intelligence.

	Full mathematics, methodology, and engineering are in *[TR‑2026‑001 — Ternary Foundations for Efficient, Sovereign AI](https://doi.org/10.5281/zenodo.21110909)* (Zenodo, DOI [10.5281/zenodo.21110909](https://doi.org/10.5281/zenodo.21110909)).

	---

	## Files

	\| File \| Size \| Format \|
	\|---\|---\|---\|
	\| `terna-e2b-Q2_K.gguf` \| ~3.6 GB \| GGUF (`Q2_K`) — runs on llama.cpp \|

	---

	## Usage

	This is a standard GGUF and runs on [`llama.cpp`](https://github.com/ggml-org/llama.cpp).

	Quick test (CLI):

	```bash
	llama-cli -m terna-e2b-Q2_K.gguf -p "Explain what a mitochondrion does, in two sentences." --temp 0.7
	```

	Serve an OpenAI‑compatible endpoint:

	```bash
	llama-server \
	-m terna-e2b-Q2_K.gguf \
	-c 4096 --host 127.0.0.1 --port 8000
	```

	Then POST to `http://127.0.0.1:8000/v1/chat/completions`. The Gemma‑4 chat template ships in the GGUF and is applied automatically when you use the chat endpoint.

	### Recommended generation settings

	This checkpoint has a low‑entropy output distribution (very confident). For anything beyond short answers, soften it:

	- `temperature: 0.7`
	- a mild repetition penalty (e.g. `--repeat-penalty 1.2`) for long‑form generations, to avoid rigidity/repetition

	---

	## Intended use

	- Research and community evaluation of ternary distillation and efficient serving.
	- Efficiency / systems experimentation — edge, memory‑constrained, and legacy‑GPU serving where footprint dominates.
	- Best behaved in well‑covered domains: general science, biology, medicine (educational), mathematics, and computer science.

	### Out of scope / not recommended (for this pre‑release)

	- Production or high‑stakes use of any kind. This is an early checkpoint.
	- Unverified factual, medical, legal, or safety‑critical output. The model is confident even when wrong — a human must verify.
	- Long‑context or long‑form tasks without the softened sampling above.

	---

	## Limitations & known behaviors

	Honest notes from our own evaluation of this checkpoint:

	- Confidently wrong. High top‑1 confidence means errors are stated as fluently and assertively as correct answers. Do not treat outputs as facts without checking.
	- Low entropy → rigidity. Peaked output distribution can make long generations repetitive or rigid; mitigate with the recommended sampling.
	- Echo‑loops on out‑of‑distribution inputs. Limited chat‑format training means unusual phrasings or niche topics can trigger repetition/echoing. Stays healthiest in the well‑covered domains listed above.
	- English‑centric, small effective size, and inherits any biases/limitations of the Gemma‑4‑E2B base.
	- Pre‑release quality. Capability is not yet benchmarked; the production (~15B‑token) release is the intended quality bar.

	---

	## Training & method (summary)

	The ternary student is trained under quantization‑aware objectives that align its outputs and intermediate representations to the Gemma‑4‑E2B teacher, so the { −1, 0, +1 } constraint is learned during training rather than applied afterward. Language‑model linear layers are ternarized; embeddings, the LM head, and normalization layers are kept at higher precision. Serving optimizations are held to a token‑identical correctness gate against a reference path, so throughput work never silently changes outputs.

	Exact data mixes, hyperparameters, and kernel/encoding internals are held proprietary; the methods and mental models are described in the Institute's technical reports.

	---

	## About the GoAutomate AI Institute

	The [GoAutomate AI Institute](https://www.goautomate.institute) is a not‑for‑profit advancing Canadian sovereign AI — accessible, responsible, Canadian‑governed models for organizations across Canada, with a focus on efficiency and on sectors where provenance and governability matter (healthcare, public sector, critical infrastructure). Ternary is our bet on the next wave of efficient AI: capability that scales down in cost as readily as it scales up in ability.

	---

	## License

	This model is a derivative of Gemma‑4‑E2B and is governed by the [Gemma Terms of Use](https://ai.google.dev/gemma/terms). By downloading or using these weights you agree to those terms. Gemma is provided under and subject to the Gemma Terms of Use.

	---

	## Citation

	```bibtex
	@techreport{goautomate2026ternary,
	title = {Ternary Foundations for Efficient, Sovereign AI},
	author = {{GoAutomate AI Institute}},
	institution = {GoAutomate AI Institute},
	number = {TR-2026-001},
	year = {2026},
	doi = {10.5281/zenodo.21110909},
	url = {https://doi.org/10.5281/zenodo.21110909},
	note = {Pre-release; ternary-distilled Gemma-4-E2B}
	}
	```

	---

	## Contact

	Questions, evaluation feedback, or collaboration: [info@goautomate.ai](mailto:info@goautomate.ai) · [goautomate.institute](https://www.goautomate.institute)

	<div align="center">
	<sub>© 2026 GoAutomate AI Institute · Canadian Sovereign AI · Responsible Adoption · Public Benefit</sub>
	</div>