Searchless Chess 9M Dpo

14
1
3 languages
license:apache-2.0
by
dbest-isi
Other
OTHER
New
14 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
Unknown
Mobile
Laptop
Server
Quick Summary

This is a 9 million parameter transformer-based chess engine trained using Direct Preference Optimization (DPO) with mistake-focused self-play and Stockfish supervision.

Code Examples

Installationbash
pip install jax jaxlib dm-haiku orbax-checkpoint numpy huggingface-hub python-chess
Installationbash
pip install jax jaxlib dm-haiku orbax-checkpoint numpy huggingface-hub python-chess

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.