Downloads · 30 days
5
4% of all-time downloads
i-sanjay-cs/bible-tinyllama
bible-tinyllama is a machine learning model from i-sanjay-cs. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
python from transformers import pipeline
Downloads · 30 days
5
4% of all-time downloads
All-time downloads
120
Public
Parameters
1.1B
2.2 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors2.2 GB · 100%
From the Hugging Face model README
---
library_name: transformers
base_model: unsloth/TinyLlama-1.1B-bnb-4bit
language:
- en
license: mit
tags:
- bible
- kjv
- christian
- tinyllama
- unsloth
- text-generation
pipeline_tag: text-generation
datasets:
- gutenberg
widget:
- text: "What does the Bible say about prayer?"
model-index:
- name: Bible TinyLlama
results:
- task:
type: text-generation
dataset:
name: Custom Bible Q&A
type: custom
metrics:
- name: Custom eval
type: custom
value: N/A
---
# Bible TinyLlama (1.1B) 🧠📖
**Personal Bible scholar** fine-tuned on **full KJV Bible** + 800 Q&A pairs.
## 🚀 Quickstart
```python
from transformers import pipeline
pipe = pipeline("text-generation",
"i-sanjay-cs/bible-tinyllama",
torch_dtype="auto",
device_map="auto")
result = pipe("Bible scholar:\nQ: Greatest commandment?\nA:",
max_new_tokens=150, temperature=0.1)
print(result["generated_text"])
Bible scholar using KJV:
Q: [question]
A:
| Property | Value |
|---|---|
| Size | 1.1B params |
| Training | Unsloth QLoRA (60 steps) |
| Data | KJV Bible + Q&A |
| RAM | 3GB CPU / 2GB GPU |
Ollama:
ollama create biblegpt -m i-sanjay-cs/bible-tinyllama
ollama run biblegpt
Gradio:
import gradio as gr
gr.ChatInterface(lambda q: pipe(f"Bible: {q}\nA:", max_new_tokens=150)["generated_text"]).launch()
Q: Greatest commandment?
A: Love the Lord thy God with all thy heart...
Q: Loving enemies?
A: Love your enemies, bless them that curse you...
By i-sanjay-cs | Unsloth QLoRA | KJV Bible