🚀 Local LLM Chat with Hugging Face Transformers

This repository accompanies the YouTube tutorial demonstrating how to run a local large language model (LLM) using Hugging Face Transformers. The provided Python script implements a complete workflow for chat-style interactions with a locally stored model.

LLM MODEL

📚 Table of Contents

• Features
• Prerequisites
• Installation
• Usage
• Code Structure
• Configuration
• Contributing
• License
• Resources

🌟 Features

• Local Model Loading 🔄
  Load pretrained causal language models from local checkpoints
• Chat Template Formatting 💬
  Supports conversational message formatting
• Smart Tokenization 🔠
  Includes attention masking and device allocation
• Controlled Generation 🎛️
  Configurable parameters:
  • Temperature
  • Top-p sampling
  • Max new tokens
• Cross-Platform Support 💻
  Works on CPU (CUDA supported for GPU acceleration)

🛠️ Prerequisites

• Python 3.7+
• PyTorch (CPU/CUDA version)
• Hugging Face Transformers
• 8GB+ RAM (16GB recommended)

📥 Installation

# Clone repository
git clone https://github.com/portalbh/SmolLM2.git
cd SmolLM2

# Create virtual environment (recommended)
python -m venv venv
source venv/bin/activate  # Linux/macOS
venv\Scripts\activate    # Windows

# Install dependencies
pip install torch transformers