Skip to main content

End-to-end LLM model building, fine-tuning, and deployment toolkit

Project description


license: apache-2.0 base_model:

  • mistralai/Mistral-7B-Instruct-v0.3 pipeline_tag: translation tags:
  • llm
  • devops
  • development
  • polish
  • english
  • python
  • iac

🚀 WronAI - End-to-End LLM Toolkit

PyPI Version Python Version License Tests Code Style Documentation Docker Pulls

A comprehensive toolkit for creating, fine-tuning, and deploying large language models with support for both Polish and English.

🌟 Features

  • Ready-to-use WronAI package - All functionality available through the wronai package
  • Model Management - Easy installation and management of LLM models
  • Multiple Model Support - Works with various models via Ollama
  • Optimizations - 4-bit quantization, LoRA, FP16 support
  • CLI Tools - Command-line interface for all operations
  • Production Ready - Easy deployment with Docker
  • Web Interface - User-friendly Streamlit-based web UI

🚀 Quick Start

Prerequisites

  • Python 3.8+
  • Ollama installed and running
  • CUDA (optional, for GPU acceleration)

Installation

# Install the package
pip install wronai

# Start Ollama (if not already running)
ollama serve &

# Pull the required model (e.g., mistral:7b-instruct)
ollama pull mistral:7b-instruct

Basic Usage

Using Python Package

from wronai import WronAI

# Initialize with default settings
wron = WronAI()

# Chat with the model
response = wron.chat("Explain quantum computing in simple terms")
print(response)

Command Line Interface

# Start interactive chat
wronai chat

# Run a single query
wronai query "Explain quantum computing in simple terms"

Web Interface

# Start the web UI
wronai web

🔧 Model Management

List available models:

ollama list

Pull a model (if not already available):

ollama pull mistral:7b-instruct

🐳 Docker Support

Run with Docker:

docker run -p 8501:8501 wronai/wronai web

🛠️ Development

Installation from Source

# Clone the repository
git clone https://github.com/wronai/llm-demo.git
cd llm-demo

# Install in development mode
pip install -e ".[dev]"

# Install pre-commit hooks
pre-commit install

Running Tests

# Run all tests
pytest

# Run with coverage
pytest --cov=wronai --cov-report=term-missing

🤝 Contributing

Contributions are welcome! Please see our Contributing Guide for details.

📜 License

This project is licensed under the Apache 2.0 License - see the LICENSE file for details.

📧 Contact

For questions or support, please open an issue on GitHub or contact us at [email protected]

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

wronai-0.1.5.tar.gz (20.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

wronai-0.1.5-py3-none-any.whl (24.6 kB view details)

Uploaded Python 3

File details

Details for the file wronai-0.1.5.tar.gz.

File metadata

  • Download URL: wronai-0.1.5.tar.gz
  • Upload date:
  • Size: 20.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.1.3 CPython/3.12.4 Linux/6.14.9-300.fc42.x86_64

File hashes

Hashes for wronai-0.1.5.tar.gz
Algorithm Hash digest
SHA256 6d35a88d95aa3885dd4e333d7bec66d3a6ea146948b2727aeb4bf817241a233a
MD5 c4b78e26f42f238344c1d57931935b17
BLAKE2b-256 64ddf44ae740e3ac34d5758c69774dfdd09b722f0125c3dcf1986b1ec18c2477

See more details on using hashes here.

File details

Details for the file wronai-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: wronai-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 24.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.1.3 CPython/3.12.4 Linux/6.14.9-300.fc42.x86_64

File hashes

Hashes for wronai-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 e64df8fd128010bd2bf86fbcd85b1e3947dae93b3f7567336d7820d1d27684e6
MD5 599b2ddda3f00f712c1ad6340caa9076
BLAKE2b-256 f3abcccebfeb88b0dee626e82a4d2781050d0f8541d490fcecf8e238863c0ec9

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page