https://github.com/shiva-prasad-naroju/blog-generator
A lightweight Streamlit app that generates blog content using a locally hosted, quantized LLaMA 2 model.
https://github.com/shiva-prasad-naroju/blog-generator
genai genai-chatbot llama2 metaai
Last synced: 4 months ago
JSON representation
A lightweight Streamlit app that generates blog content using a locally hosted, quantized LLaMA 2 model.
- Host: GitHub
- URL: https://github.com/shiva-prasad-naroju/blog-generator
- Owner: Shiva-Prasad-Naroju
- Created: 2025-06-15T13:54:28.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2025-06-15T14:39:07.000Z (4 months ago)
- Last Synced: 2025-06-15T15:44:33.574Z (4 months ago)
- Topics: genai, genai-chatbot, llama2, metaai
- Language: Python
- Homepage:
- Size: 28.3 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# LLaMA 2 Blog Generator
A lightweight Streamlit application that generates human-like blog content using a locally hosted **LLaMA 2** model. Designed for low-end systems, this project eliminates the need for cloud-based APIs by running entirely on your machine with a quantized `.ggml` model.
## 🚀 What It Does
- 📝 Generates blog posts from a topic and selected writing style.
- 🎛️ Customizable word length and tone.
- ⚡ Runs efficiently on low-spec laptops using quantized inference.
## 🧠 Technology Stack
- **LLaMA 2 (Quantized)** – Local language model (e.g., `ggmlv3.q8_0.bin`)
- **CTransformers** – For loading and running LLaMA 2 without GPUs
- **LangChain** – Prompt templating and model invocation
- **Streamlit** – Simple UI for topic input and result display
## ✅ Use Cases
- 📚 Quick blog drafts for content creators
- 🧪 Experimentation with LLMs
- 🧑🎓 Educational tool to learn LLM workflows
- 🔌 API-free solution for writing assistance
## 💻 Requirements
- Python 3.9+
- Minimum 8 GB RAM (recommended)
- Local storage for model (~4–5 GB)
- 2 CPU cores (minimum)
## Result UI:
