Instructions to use upfall-co/voidx-decider-12b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use upfall-co/voidx-decider-12b-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 upfall-co/voidx-decider-12b-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf upfall-co/voidx-decider-12b-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf upfall-co/voidx-decider-12b-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf upfall-co/voidx-decider-12b-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf upfall-co/voidx-decider-12b-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf upfall-co/voidx-decider-12b-GGUF:Q4_K_M
Use Docker
docker model run hf.co/upfall-co/voidx-decider-12b-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use upfall-co/voidx-decider-12b-GGUF with Ollama:
ollama run hf.co/upfall-co/voidx-decider-12b-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use upfall-co/voidx-decider-12b-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf upfall-co/voidx-decider-12b-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "upfall-co/voidx-decider-12b-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use upfall-co/voidx-decider-12b-GGUF with Docker Model Runner:
docker model run hf.co/upfall-co/voidx-decider-12b-GGUF:Q4_K_M
- Lemonade
How to use upfall-co/voidx-decider-12b-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull upfall-co/voidx-decider-12b-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.voidx-decider-12b-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use upfall-co/voidx-decider-12b-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 upfall-co/voidx-decider-12b-GGUF:Q4_K_M
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://127.0.0.1:9931/v1 hermes config set model.default upfall-co/voidx-decider-12b-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use upfall-co/voidx-decider-12b-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf upfall-co/voidx-decider-12b-GGUF:Q4_K_M
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://127.0.0.1:9931/v1 \ --custom-model-id "upfall-co/voidx-decider-12b-GGUF:Q4_K_M" \ --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"
voidx-decider-12b-GGUF
Q4_K_M GGUF of voidx-decider-12b:
the LoRA adapter merged into google/gemma-4-12B-it (revision 707f0a3b), then
quantized with llama.cpp. This is not an official Google model.
| File | Size | sha256 |
|---|---|---|
voidx-decider-12b-Q4_K_M.gguf |
7.38 GB | c48d1fc0851d5bf368a93e07efe725dd2235145e5dbd8877df9eeeaf408195d1 |
Research release. The model did not pass its locked-test gate and is highly vulnerable to prompt injection. See the main model card for usage, evaluation and limitations.
- Q4_K_M vs bf16 on the locked test: accuracy 78.4% vs 79.3%, ECE 0.034 vs 0.028.
- Serving temperature: T = 0.98580.
- llama-server: use
/completionwithn_probs, or passchat_template_kwargs: {"enable_thinking": false}on the chat endpoint.
License: Apache-2.0. See LICENSE and NOTICE.
- Downloads last month
- 25
4-bit