Instructions to use Babsie/OmegaDirective-70B-6Q-Merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Babsie/OmegaDirective-70B-6Q-Merged with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Babsie/OmegaDirective-70B-6Q-Merged",
	filename="Loki-Omega-70B-6QMerged.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Babsie/OmegaDirective-70B-6Q-Merged with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Babsie/OmegaDirective-70B-6Q-Merged
# Run inference directly in the terminal:
llama-cli -hf Babsie/OmegaDirective-70B-6Q-Merged

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Babsie/OmegaDirective-70B-6Q-Merged
# Run inference directly in the terminal:
llama-cli -hf Babsie/OmegaDirective-70B-6Q-Merged

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 Babsie/OmegaDirective-70B-6Q-Merged
# Run inference directly in the terminal:
./llama-cli -hf Babsie/OmegaDirective-70B-6Q-Merged

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 Babsie/OmegaDirective-70B-6Q-Merged
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Babsie/OmegaDirective-70B-6Q-Merged

Use Docker

docker model run hf.co/Babsie/OmegaDirective-70B-6Q-Merged

LM Studio
Jan
Ollama
How to use Babsie/OmegaDirective-70B-6Q-Merged with Ollama:
```
ollama run hf.co/Babsie/OmegaDirective-70B-6Q-Merged
```

Unsloth Studio new

How to use Babsie/OmegaDirective-70B-6Q-Merged 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 Babsie/OmegaDirective-70B-6Q-Merged 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 Babsie/OmegaDirective-70B-6Q-Merged to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Babsie/OmegaDirective-70B-6Q-Merged to start chatting

Pi new

How to use Babsie/OmegaDirective-70B-6Q-Merged with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Babsie/OmegaDirective-70B-6Q-Merged

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": "Babsie/OmegaDirective-70B-6Q-Merged"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Babsie/OmegaDirective-70B-6Q-Merged with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Babsie/OmegaDirective-70B-6Q-Merged

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 Babsie/OmegaDirective-70B-6Q-Merged

Run Hermes

hermes

Docker Model Runner
How to use Babsie/OmegaDirective-70B-6Q-Merged with Docker Model Runner:
```
docker model run hf.co/Babsie/OmegaDirective-70B-6Q-Merged
```

Lemonade

How to use Babsie/OmegaDirective-70B-6Q-Merged with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Babsie/OmegaDirective-70B-6Q-Merged

Run and chat with the model

lemonade run user.OmegaDirective-70B-6Q-Merged-{{QUANT_TAG}}

List all available models

lemonade list

Loki-Omega-70B-6QMerged-GGUF

This repository contains a single merged GGUF file for running ReadyArt/L3.3-The-Omega-Directive-70B-Unslop-v2.0 with llama.cpp (Q6_K quantization).

File

Loki-Omega-70B-6QMerged.gguf (57GB) - Full merged model, ready to use

Quick Start (llama.cpp server, OpenAI-compatible)

pip install "llama-cpp-python[server]"
python -m llama_cpp.server \
  --model /path/to/Loki-Omega-70B-6QMerged.gguf \
  --host 0.0.0.0 --port 8000 \
  --n_ctx 32000

## Quantization: Q6_K (maintains quality and nuance)
Note: This is the merged version. For split files, see the original repository.

Downloads last month: 4

GGUF

Model size

71B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for Babsie/OmegaDirective-70B-6Q-Merged

Base model

Steelskull/L3.3-MS-Nevoria-70b

Finetuned

ReadyArt/L3.3-The-Omega-Directive-70B-Unslop-v2.0

Quantized

(4)

this model