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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use rhemabible/GemmaBible 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 rhemabible/GemmaBible:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf rhemabible/GemmaBible:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rhemabible/GemmaBible:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf rhemabible/GemmaBible: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 rhemabible/GemmaBible:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf rhemabible/GemmaBible: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 rhemabible/GemmaBible:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rhemabible/GemmaBible:Q5_K_M

Use Docker

docker model run hf.co/rhemabible/GemmaBible:Q5_K_M

LM Studio
Jan

vLLM

How to use rhemabible/GemmaBible with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rhemabible/GemmaBible"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rhemabible/GemmaBible",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rhemabible/GemmaBible:Q5_K_M

Ollama
How to use rhemabible/GemmaBible with Ollama:
```
ollama run hf.co/rhemabible/GemmaBible:Q5_K_M
```
Unsloth Desktop

How to use rhemabible/GemmaBible with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rhemabible/GemmaBible:Q5_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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "rhemabible/GemmaBible:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use rhemabible/GemmaBible with Docker Model Runner:
```
docker model run hf.co/rhemabible/GemmaBible:Q5_K_M
```

Lemonade

How to use rhemabible/GemmaBible with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rhemabible/GemmaBible:Q5_K_M

Run and chat with the model

lemonade run user.GemmaBible-Q5_K_M

List all available models

lemonade list

Hermes Agent

How to use rhemabible/GemmaBible with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rhemabible/GemmaBible: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 rhemabible/GemmaBible:Q5_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use rhemabible/GemmaBible with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rhemabible/GemmaBible:Q5_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://127.0.0.1:8080/v1 \
  --custom-model-id "rhemabible/GemmaBible:Q5_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"

GemmaBible / README.md

robzilla1738

Upload README.md with huggingface_hub

58652ef verified 6 months ago

2.2 kB

license: apache-2.0
base_model: google/gemma-4-E4B-it
tags:
  - bible
  - theology
  - gemma4
  - fine-tuned
  - qlora
language:
  - en
pipeline_tag: text-generation

GemmaBible

A fine-tuned Gemma 4 E4B model specialized in biblical scholarship, theology, and Bible study. Grounded in the Berean Standard Bible (BSB).

What it does

Quotes Scripture precisely from the BSB with proper citations
Provides Greek and Hebrew word studies with transliterations and Strong's numbers
Presents Protestant, Catholic, and Orthodox perspectives on debated topics
Analyzes passages with scholarly hermeneutics and cited sources
Detects and corrects common misquotations
Stays within theological boundaries — declines non-theological requests

Training

Base model: google/gemma-4-E4B-it (4.5B effective parameters)
Method: QLoRA (rank 64, alpha 64) with Unsloth
Data: ~8,000 instruction examples across 11 specialized generators covering comparative theology, Greek/Hebrew exegesis, systematic theology, creedal analysis, and more
Hardware: NVIDIA RTX PRO 6000 (96GB)
Epochs: 3 | Final loss: 0.40

Usage

With Ollama (GGUF)

Download merged.Q5_K_M.gguf and create a Modelfile:

FROM ./merged.Q5_K_M.gguf
PARAMETER temperature 0.3
PARAMETER top_p 0.9
PARAMETER num_ctx 4096

ollama create gemmabible -f Modelfile
ollama run gemmabible "What does John 3:16 mean?"

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("rhemabible/GemmaBible")
tokenizer = AutoTokenizer.from_pretrained("rhemabible/GemmaBible")

Files

File	Format	Size	Use
`model.safetensors`	SafeTensors	~15 GB	Full precision weights
`merged.Q5_K_M.gguf`	GGUF	~5.5 GB	Ollama / LM Studio / llama.cpp

Limitations

Trained on BSB text; may be less accurate with other Bible translations
4.5B parameters — less capacity for nuanced multi-turn theological debate compared to larger models
Not a substitute for pastoral counsel or formal theological education