Instructions to use ShiroOnigami23/THE_ARCHITECT_V2_FINAL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ShiroOnigami23/THE_ARCHITECT_V2_FINAL with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ShiroOnigami23/THE_ARCHITECT_V2_FINAL",
	filename="THE_ARCHITECT_V2_FINAL.Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ShiroOnigami23/THE_ARCHITECT_V2_FINAL 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 ShiroOnigami23/THE_ARCHITECT_V2_FINAL:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ShiroOnigami23/THE_ARCHITECT_V2_FINAL:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ShiroOnigami23/THE_ARCHITECT_V2_FINAL:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ShiroOnigami23/THE_ARCHITECT_V2_FINAL:Q4_K_M

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 ShiroOnigami23/THE_ARCHITECT_V2_FINAL:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ShiroOnigami23/THE_ARCHITECT_V2_FINAL:Q4_K_M

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 ShiroOnigami23/THE_ARCHITECT_V2_FINAL:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ShiroOnigami23/THE_ARCHITECT_V2_FINAL:Q4_K_M

Use Docker

docker model run hf.co/ShiroOnigami23/THE_ARCHITECT_V2_FINAL:Q4_K_M

LM Studio
Jan
Ollama
How to use ShiroOnigami23/THE_ARCHITECT_V2_FINAL with Ollama:
```
ollama run hf.co/ShiroOnigami23/THE_ARCHITECT_V2_FINAL:Q4_K_M
```

Unsloth Studio

How to use ShiroOnigami23/THE_ARCHITECT_V2_FINAL 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 ShiroOnigami23/THE_ARCHITECT_V2_FINAL 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 ShiroOnigami23/THE_ARCHITECT_V2_FINAL to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ShiroOnigami23/THE_ARCHITECT_V2_FINAL to start chatting

Atomic Chat new
Docker Model Runner
How to use ShiroOnigami23/THE_ARCHITECT_V2_FINAL with Docker Model Runner:
```
docker model run hf.co/ShiroOnigami23/THE_ARCHITECT_V2_FINAL:Q4_K_M
```

Lemonade

How to use ShiroOnigami23/THE_ARCHITECT_V2_FINAL with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ShiroOnigami23/THE_ARCHITECT_V2_FINAL:Q4_K_M

Run and chat with the model

lemonade run user.THE_ARCHITECT_V2_FINAL-Q4_K_M

List all available models

lemonade list

🏗️ THE ARCHITECT: GHOST CODEX OMEGA V2.5

Project Classification: BLACK SITE / ZERO-COST FORTRESS

This repository serves as the central hub for the Architect Ecosystem. It is a high-fidelity LaTeX workstation designed for secure, zero-cost architectural drafting and technical documentation.

🛠️ System Architecture

The project is split into three distinct, synchronized layers:

Logic Tier (The Brain): A fine-tuned GGUF Model running locally via Ollama to ensure 100% prompt privacy and zero-latency inference.
Forge Tier (The Interface): A supreme CustomTkinter GUI (.exe) featuring real-time streaming, split-pane code monitoring, and project archiving.
Compiler Tier (The Factory): A private Docker-based TeX Live Space hosted on Hugging Face that handles heavy PDF rendering without requiring local installations.

📜 Omega Protocol Features

Live Forge Monitor: Real-time streaming of LaTeX logic directly into the UI.
Style Protocol Injection: Dropdown presets that automatically configure the AI for TikZ, PGFPlots, or Scientific formatting.
Full Project Archiving: One-click export of the raw instructions (.txt), the source code (.tex), and the final render (.pdf).
Zero-Weight Portability: The standalone executable requires no local LaTeX distribution (MiKTeX/TeX Live) to function.

🚀 Deployment Instructions

Local PC Setup

Download the GGUF Model from ShiroOnigami23/THE_ARCHITECT_V2_FINAL.
Initialize the model in Ollama: ollama create architect-v2 -f Modelfile.
Run the Architect_Omega.exe.

Cloud Infrastructure

Model Engine: THE_ARCHITECT_V2_FINAL
Training Ground: ARCHITECT-HIGH-FID-100K
Compiler Core: LATEX-COMPILER-CORE

Security Rating: 9.5/10 (Post-Quantum & Anti-Intelligence Resistant) Developed by: ShiroOnigami23

Downloads last month: -

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support