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

Libraries

How to use xlelords/omriX with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="xlelords/omriX",
	filename="OmniCode-Pro-v1-f16.gguf",
)

llm.create_chat_completion(
	messages = "\"I like you. I love you\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use xlelords/omriX with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf xlelords/omriX:F16
# Run inference directly in the terminal:
llama-cli -hf xlelords/omriX:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf xlelords/omriX:F16
# Run inference directly in the terminal:
llama-cli -hf xlelords/omriX:F16

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 xlelords/omriX:F16
# Run inference directly in the terminal:
./llama-cli -hf xlelords/omriX:F16

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 xlelords/omriX:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf xlelords/omriX:F16

Use Docker

docker model run hf.co/xlelords/omriX:F16

LM Studio
Jan
Ollama
How to use xlelords/omriX with Ollama:
```
ollama run hf.co/xlelords/omriX:F16
```

Unsloth Studio new

How to use xlelords/omriX 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 xlelords/omriX 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 xlelords/omriX to start chatting

Using HuggingFace Spaces for Unsloth

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

Pi new

How to use xlelords/omriX with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf xlelords/omriX:F16

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": "xlelords/omriX:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use xlelords/omriX with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf xlelords/omriX:F16

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 xlelords/omriX:F16

Run Hermes

hermes

Docker Model Runner
How to use xlelords/omriX with Docker Model Runner:
```
docker model run hf.co/xlelords/omriX:F16
```

Lemonade

How to use xlelords/omriX with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull xlelords/omriX:F16

Run and chat with the model

lemonade run user.omriX-F16

List all available models

lemonade list

🚀 omriX

A well-trained small coding agent that is very quick.

omriX is a lightweight, open-source coding-focused model designed for speed, efficiency, and practical developer workflows. With a compact disk size of roughly 3 GB, it’s ideal for local inference, low-cost deployments, and experimentation without heavy hardware requirements.

✨ Key Features

⚡ Fast inference — optimized for quick responses
🧠 Coding-focused — tuned for programming and code-related tasks
📦 Lightweight — ~3 GB disk size
🔓 Open source — Apache-2.0 license
💸 Cheap to run — suitable for low-resource environments
🤖 Agent-friendly — works well as a small coding agent component

🧩 Use Cases

Code understanding & classification
Lightweight coding assistants
Student projects / FYPs
Local developer tools
Agent pipelines requiring fast, small models
Prototyping and experimentation

📥 Model Details

Model ID: xlelords/omriX
License: Apache-2.0
Language: English
Pipeline Tag: Text Classification
Disk Size: ~3 GB
Status: Fully open-source

🚀 Quick Start

Example usage with 🤗 Transformers:

from transformers import AutoTokenizer, AutoModelForSequenceClassification

model_id = "xlelords/omriX"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSequenceClassification.from_pretrained(model_id)

text = "Explain what this function does: def add(a, b): return a + b"

inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)

print(outputs.logits)

⚠️ Note: The pipeline interface depends on your downstream setup.
omriX is commonly used as a component model inside agents or custom pipelines.

🛠️ Agent Integration

omriX is well-suited for use in lightweight agent frameworks such as:

Custom Python agents
Tool-calling pipelines
smolagents-style workflows
Local or edge deployments

Its small size and fast responses make it ideal for chaining with tools or running alongside other models.

📄 License

This model is released under the Apache-2.0 License.
You are free to use, modify, distribute, and build upon it — even commercially.

🤝 Contributing

Contributions are welcome!
Feel free to open issues or pull requests for:

Documentation improvements
Benchmarks
Agent examples
Optimized inference setups

⭐ Final Notes

If you’re looking for a fast, cheap, and capable small coding agent, omriX is built to get out of your way and let you ship.

Enjoy 🚀

Downloads last month: 15

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

16-bit