Instructions to use DemonKing1234/gt730-moe-transformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use DemonKing1234/gt730-moe-transformer 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 DemonKing1234/gt730-moe-transformer:F32
# Run inference directly in the terminal:
llama cli -hf DemonKing1234/gt730-moe-transformer:F32

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DemonKing1234/gt730-moe-transformer:F32
# Run inference directly in the terminal:
llama cli -hf DemonKing1234/gt730-moe-transformer:F32

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 DemonKing1234/gt730-moe-transformer:F32
# Run inference directly in the terminal:
./llama-cli -hf DemonKing1234/gt730-moe-transformer:F32

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 DemonKing1234/gt730-moe-transformer:F32
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DemonKing1234/gt730-moe-transformer:F32

Use Docker

docker model run hf.co/DemonKing1234/gt730-moe-transformer:F32

LM Studio
Jan

vLLM

How to use DemonKing1234/gt730-moe-transformer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DemonKing1234/gt730-moe-transformer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DemonKing1234/gt730-moe-transformer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DemonKing1234/gt730-moe-transformer:F32

Ollama
How to use DemonKing1234/gt730-moe-transformer with Ollama:
```
ollama run hf.co/DemonKing1234/gt730-moe-transformer:F32
```
Unsloth Desktop
Docker Model Runner
How to use DemonKing1234/gt730-moe-transformer with Docker Model Runner:
```
docker model run hf.co/DemonKing1234/gt730-moe-transformer:F32
```

Lemonade

How to use DemonKing1234/gt730-moe-transformer with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DemonKing1234/gt730-moe-transformer:F32

Run and chat with the model

lemonade run user.gt730-moe-transformer-F32

List all available models

lemonade list

Atomic Chat

🧠 GT-730 MoE Reasoning Transformer (GGUF)

DemonKing1234/gt730-moe-transformer is a lightweight, edge-optimized Mixture-of-Experts (MoE) Language Model designed for efficient token generation, algorithmic problem-solving, and agentic reasoning on low-resource hardware.

🚀 What This Model Can Do & What It's Used For

1. 🐍 Python Code & Algorithm Generation

Trained on Python data structures, algorithms (binary search trees, graphs, sorting, async operations), and common developer patterns. It can generate small code snippets, logic blocks, and algorithmic skeletons.

2. 🤖 Agentic Problem Solving & Tool-Use

Employs step-by-step reasoning tokens ( chains) and action simulation (ACTION: write_file, un_command), enabling it to simulate autonomous assistant and tool-use behaviors.

3. 🧩 Multi-Step Logic & Math Reasoning

Leverages MoE routing to direct logic and mathematical steps through specialized feed-forward expert networks for structured, multi-step problem solving.

4. ⚡ Ultra-Efficient Edge Inference

Because the model uses a sparse Mixture-of-Experts architecture with top-k gating, only a fraction of the network parameters are activated per token, making it fast and lightweight for edge devices, CPUs, and low-end GPUs.

📊 Model Architecture & Specifications

Parameter	Value
Architecture	Causal Mixture-of-Experts (MoE) Transformer
Layers	5 Transformer Blocks
Routing / Experts	16 Feed-Forward Experts (Top-2 Activated per token)
Attention Heads	4 Heads with Causal Masking
Hidden Size	64
Feed-Forward Dimension	128
Vocabulary Size	2,386 Tokens
Precision	FP32 (GGUF Format)
Weight File	moe_reasoning_transformer_f32.gguf (8.86 MB)

📈 Training Details & Token Count

Metric	Details
Total Cumulative Tokens Trained	~175,000,000+ Tokens (~175M token exposures across pretraining passes)
Base Corpus Size	~~2.1 Million Characters (~~400,000 base tokens)
Training Passes / Epochs	300 to 500 iterative optimization epochs
Hardware	NVIDIA GeForce GT 730 (CUDA) + Multi-Core CPU
Frameworks	JAX/Flax & CuPy

📚 Training Dataset (Mega Hybrid Corpus)

Pretrained on a curated dataset combining:

High-performance Python codebases, data structures, and algorithms
Agentic scratchpads and structured chain-of-thought demonstrations ()
Step-by-step mathematical & logical reasoning samples (GSM8K/MATH style)
Literary knowledge & structured conversational dialogues

⚙️ Intended Use & Limitations

Intended For: Research into sparse MoE scaling on ultra-constrained edge devices, offline embedded AI experiments, and fast local prototyping.
Limitations: As a micro-scale model (8.86 MB), it is optimized for compactness and structural reasoning rather than expansive general world knowledge.

Downloads last month: 17

GGUF

Model size

2.21M params

Architecture

gt730_moe

Hardware compatibility

32-bit

DemonKing1234
/

gt730-moe-transformer