OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Chess Transformers

Chess Transformers is a Python library for training transformer models to play chess by learning from human games. It includes workflows for preparing datasets, training and evaluating models, and playing games against people or chess engines.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Chess Transformers — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a code-based workflow for training or studying transformer chess models from human games, rather than only playing chess through a standalone website or app.

Who it is for

  • Researchers and developers experimenting with transformer-based chess models.
  • Python users who want to train models from human chess-game data.
  • Developers comparing model predictions or evaluating chess models against engines.

Documented uses

  • Prepare chess-game training data for a configured model.
  • Train transformer models and average saved checkpoints.
  • Load documented model configurations and play human-versus-model games.
  • Play models against Stockfish or Fairy Stockfish and evaluate model results.
  • Save played games in PGN format.
Before you choose

Requirements & limits

The project is a public GitHub repository with an MIT license and documents installation as a local Python package.

  • The README lists four model configurations with different parameter counts, architectures and move-prediction formats.
  • Training and evaluation use configured data paths; model-versus-engine play can require a configured engine executable.
  • The repository documents engine evaluation and a human-play workflow, but its README says the public API is not stable.
  • The documented installation uses Python packaging; the technical listing identifies PyTorch as the ecosystem.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Chess Transformers locally

Clone the repository and install the package locally for Python development or use.

Before you start

  • Python package installation environment
  • GitHub CLI, as shown in the documented clone command

Steps

  1. Clone the sgrvinod/chess-transformers repository with the GitHub CLI.

  2. Change into the chess-transformers directory.

  3. Run pip install . to install the package locally.

  4. For code development or contribution, use pip install -e . for editable installation.

Expected outcome

The repository is installed as a local Python package; editable mode is available for development.

Guide limitations

  • This covers installation only, not training or running a model.
  • Training or evaluation may require CT_DATA_FOLDER to point to training data; engine play may require paths to Stockfish 16 or Fairy Stockfish executables.
  • The README says the public API is not stable.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
sgrvinod/chess-transformers · Official homepage title · retained in its source language
How we review sourcesSuggest a correction