Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
metadata
title: Open LLM Leaderboard
emoji: π
colorFrom: blue
colorTo: red
sdk: docker
hf_oauth: true
pinned: true
license: apache-2.0
duplicated_from: open-llm-leaderboard/open_llm_leaderboard
tags:
- leaderboard
short_description: Track, rank and evaluate open LLMs and chatbots
Open LLM Leaderboard
Modern React interface for comparing Large Language Models (LLMs) in an open and reproducible way.
Features
- π Interactive table with advanced sorting and filtering
- π Semantic model search
- π Pin models for comparison
- π± Responsive and modern interface
- π¨ Dark/Light mode
- β‘οΈ Optimized performance with virtualization
Architecture
The project is split into two main parts:
Frontend (React)
frontend/
βββ src/
β βββ components/ # Reusable UI components
β βββ pages/ # Application pages
β βββ hooks/ # Custom React hooks
β βββ context/ # React contexts
β βββ constants/ # Constants and configurations
βββ public/ # Static assets
βββ server.js # Express server for production
Backend (FastAPI)
backend/
βββ app/
β βββ api/ # API router and endpoints
β β βββ endpoints/ # Specific API endpoints
β βββ core/ # Core functionality
β βββ config/ # Configuration
β βββ services/ # Business logic services
β βββ leaderboard.py
β βββ models.py
β βββ votes.py
β βββ hf_service.py
βββ utils/ # Utility functions
Technologies
Frontend
- React
- Material-UI
- TanStack Table & Virtual
- Express.js
Backend
- FastAPI
- Hugging Face API
- Docker
Development
The application is containerized using Docker and can be run using:
docker-compose up