rootxhacker
/

HobbyLM-Omni-Chess

Model card Files Files and versions

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

HobbyLM-Omni-Chess

Chess GRPO fine-tune of rootxhacker/HobbyLM-Omni (checkpoint: final). Reward = legality + material delta + win/draw/loss vs progressive-skill Stockfish. Load exactly like the base repo (hobbylm package).

Downloads last month: 25

Safetensors

Model size

0.5B params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support