Instructions to use sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF",
	filename="reformed-christian-bible-expert-v2.1-12b-q5_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_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 sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_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 sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M

Use Docker

docker model run hf.co/sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M

LM Studio
Jan

vLLM

How to use sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M

Ollama
How to use sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF with Ollama:
```
ollama run hf.co/sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M
```

Unsloth Studio

How to use sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF 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 sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF 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 sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF to start chatting

How to use sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M

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": "sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_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://127.0.0.1:8080/v1
hermes config set model.default sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M
```

Lemonade

How to use sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF:Q5_K_M

Run and chat with the model

lemonade run user.Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF-Q5_K_M

List all available models

lemonade list

✝️ Theological Foundation

This model delivers Westminster Confession-aligned analysis with covenantal depth:

📖 Expanded Reformed Corpus - Incorporating Westminster Standards, Three Forms of Unity, and Puritan writings
⚡ Covenant Theology Focus - Enhanced understanding of redemptive history through Reformed lenses
💎 Confessional Fidelity - Maintains adherence to Reformed distinctives (TULIP, Solas, Covenant Theology)
🎓 Pastoral Applications - Improved sermon preparation and catechetical instruction
🌹 Doxological Depth - Provides insights emphasizing God's sovereignty and glory

⚙️ Technical Specifications

FULL SETTINGS and optional Pastor character card Reformed-Dave

GGUF

Quants

imatrix

Quants

EXL2

Quants

Chat Template: Mistral V3 Tekken Recommended deterministic sampler for theological precision: "temperature": 0 "top_k": 1 "dry_multiplier": 0.01

📜 Key Features

🕊️ Answers theological questions from a Reformed perspective (Westminster Standards, Three Forms of Unity)
✝️ Explains Scripture through covenant theology and redemptive-historical hermeneutics
🌍 Multilingual support for ministry in 10+ languages (English, Dutch, Korean, etc.)
🎓 Enhanced capabilities for sermon preparation, catechism instruction, and theological training
💬 Advanced roleplaying for pastoral counseling and discipleship scenarios
📖 Specializes in Reformed distinctives: Covenant Theology, Solas, TULIP, Regulative Principle

⚠️ Ethical Considerations

This model is designed to:

Maintain strict fidelity to the Westminster Confession of Faith
Promote biblical authority and Christ-centered exegesis
Support but never replace church courts and pastoral oversight

📖 Performance Notes

🔥 Maintains confessional accuracy with improved covenantal analysis
📖 Handles complex theological systems (Federal Theology, Pactum Salutis)
🧠 Excels at tracing redemptive history through Scripture
⚡ Improved handling of Reformed scholastic distinctions
🎭 Responds to nuanced theological queries with precision

🧑‍🔬 Model Authors

sleepdeprived3 (Training Data & Fine-Tuning)

Downloads last month: 4

GGUF

Model size

12B params

Architecture

llama

Hardware compatibility

5-bit

Model tree for sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF

Base model

mistralai/Mistral-Nemo-Base-2407

Finetuned

mistralai/Mistral-Nemo-Instruct-2407

Finetuned

sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B

Quantized

(9)

this model

sleepdeprived3
/

Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF

Reformed Christian Bible Expert v2.1 12B

✝️ Theological Foundation

⚙️ Technical Specifications

GGUF

imatrix

EXL2

📜 Key Features

⚠️ Ethical Considerations

📖 Performance Notes

🧑‍🔬 Model Authors

Model tree for sleepdeprived3/Reformed-Christian-Bible-Expert-v2.1-12B-Q5_K_M-GGUF