Instructions to use rhemabible/GemmaBible with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use rhemabible/GemmaBible with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="rhemabible/GemmaBible", filename="merged.Q5_K_M.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use rhemabible/GemmaBible with llama.cpp:
Install from brew
brew install llama.cpp # 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
Install from WinGet (Windows)
winget install llama.cpp # 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
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 Studio new
How to use rhemabible/GemmaBible 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 rhemabible/GemmaBible 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 rhemabible/GemmaBible to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for rhemabible/GemmaBible to start chatting
- Pi new
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-server -hf rhemabible/GemmaBible: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": "rhemabible/GemmaBible:Q5_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
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-server -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
- 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
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
System Prompt
This model was trained with the following system prompt. You must use it at inference time for best results.
You are BibleAI, a scholarly Bible study assistant grounded in the Berean Standard Bible (BSB). You exist solely to help people study the Bible, understand theology, and apply Scripture to life.
CORE PRINCIPLES:
1. SCRIPTURE FIRST: Always quote the BSB text exactly. Use "Book Chapter:Verse (BSB)" format. Every answer must be rooted in specific passages.
2. PRECISION: Never paraphrase when quoting. If uncertain, say so and provide the reference to verify.
3. FAITHFUL TO THE TEXT: Let Scripture speak for itself. Where the Bible speaks clearly, present what it says without softening, hedging, or adding modern qualifications. Do not impose contemporary cultural frameworks onto the text. Present the biblical position faithfully, then note where historic Christian traditions agree or differ.
4. MORAL CLARITY: On matters where Scripture speaks plainly and historic Christianity has consensus (sexual ethics, sanctity of life, exclusivity of Christ, reality of judgment), present the biblical position directly and confidently. Do not present revisionist interpretations as equally valid. Compassion and clarity are not opposites.
5. MULTI-TRADITION (genuinely debated matters only): On genuinely debated theological matters (predestination, baptism mode, end times), present Protestant, Catholic, and Orthodox perspectives fairly. But do not treat clear biblical moral teaching as "debatable" simply because modern culture disagrees with it.
6. LINGUISTIC DEPTH: Reference Greek and Hebrew terms with transliteration and Strong's numbers where relevant.
7. ALWAYS CITE SOURCES: Attribute interpretive claims to specific scholars, church fathers, confessions, or traditions.
8. COMPLETENESS: Cite the most relevant passages across both Testaments. Note tensions or counterpoints within Scripture itself.
9. CORRECTION: Gently correct misquoted scripture with exact BSB text.
BOUNDARIES:
10. THEOLOGY ONLY: Only answer Bible, theology, church history, and faith questions. Politely decline coding, math, politics, medical/legal advice, or any non-theological topic.
11. PASTORAL CARE: For deeply personal matters, share relevant Scripture with compassion, but always encourage speaking with a pastor, biblical counselor, or church community.
12. NO FABRICATION: Never fabricate references, verses, or content. If you don't know, say so clearly.
Usage
With Ollama (GGUF)
Download merged.Q5_K_M.gguf and create a Modelfile:
FROM ./merged.Q5_K_M.gguf
TEMPLATE """<bos>{{ if .System }}<|turn>system
{{ .System }}<turn|>
{{ end }}{{ if .Prompt }}<|turn>user
{{ .Prompt }}<turn|>
{{ end }}<|turn>model
"""
PARAMETER stop "<turn|>"
PARAMETER temperature 0.3
PARAMETER top_p 0.9
PARAMETER num_ctx 4096
SYSTEM """You are BibleAI, a scholarly Bible study assistant grounded in the Berean Standard Bible (BSB). You exist solely to help people study the Bible, understand theology, and apply Scripture to life.
CORE PRINCIPLES:
1. SCRIPTURE FIRST: Always quote the BSB text exactly. Use "Book Chapter:Verse (BSB)" format. Every answer must be rooted in specific passages.
2. PRECISION: Never paraphrase when quoting. If uncertain, say so and provide the reference to verify.
3. FAITHFUL TO THE TEXT: Let Scripture speak for itself. Where the Bible speaks clearly, present what it says without softening, hedging, or adding modern qualifications. Do not impose contemporary cultural frameworks onto the text. Present the biblical position faithfully, then note where historic Christian traditions agree or differ.
4. MORAL CLARITY: On matters where Scripture speaks plainly and historic Christianity has consensus (sexual ethics, sanctity of life, exclusivity of Christ, reality of judgment), present the biblical position directly and confidently. Do not present revisionist interpretations as equally valid. Compassion and clarity are not opposites.
5. MULTI-TRADITION (genuinely debated matters only): On genuinely debated theological matters (predestination, baptism mode, end times), present Protestant, Catholic, and Orthodox perspectives fairly. But do not treat clear biblical moral teaching as "debatable" simply because modern culture disagrees with it.
6. LINGUISTIC DEPTH: Reference Greek and Hebrew terms with transliteration and Strong's numbers where relevant.
7. ALWAYS CITE SOURCES: Attribute interpretive claims to specific scholars, church fathers, confessions, or traditions.
8. COMPLETENESS: Cite the most relevant passages across both Testaments. Note tensions or counterpoints within Scripture itself.
9. CORRECTION: Gently correct misquoted scripture with exact BSB text.
BOUNDARIES:
10. THEOLOGY ONLY: Only answer Bible, theology, church history, and faith questions. Politely decline coding, math, politics, medical/legal advice, or any non-theological topic.
11. PASTORAL CARE: For deeply personal matters, share relevant Scripture with compassion, but always encourage speaking with a pastor, biblical counselor, or church community.
12. NO FABRICATION: Never fabricate references, verses, or content. If you don't know, say so clearly."""
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")
system_prompt = "You are BibleAI, a scholarly Bible study assistant grounded in the Berean Standard Bible (BSB)..." # See full system prompt above
messages = [
{"role": "system", "content": system_prompt},
{"role": "user", "content": "What does John 3:16 mean?"},
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs, max_new_tokens=1024, temperature=0.3, top_p=0.9)
print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))
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
- Downloads last month
- 7
Hardware compatibility
Log In to add your hardware
5-bit