UniMaia-Aux
UniMaia-Aux is a 3,169,644,445-parameter prompt-conditioned chess policy
model from
UniMaia: Steering Chess Policies with Language for Human-like
Play. It combines an Lc0 attention-body
policy network with a LoRA-adapted ChessGPT text encoder and ControlNet-style
conditioning. Alongside move probabilities, this variant can return value, moves-left, termination-type, and move-delay predictions.
Usage
Install chessnets with its UniMaia inference dependencies, then provide a PGN
prefix and a natural-language description of the desired player or behavior:
1from chessnets import AutoPipeline
2
3pipeline = AutoPipeline.from_pretrained("shermansiu/unimaia-aux", device="cuda")
4predictions = pipeline.make_prediction(
5 pgns="1. e4 e5 2. Nf3 Nc6 *",
6 prompts="A cautious club player is playing White.",
7 time_controls="300+3",
8 white_clock_times=[300.0, 298.0, 294.0],
9 black_clock_times=[300.0, 297.0],
10)
11print(predictions[0].best_move_san)
PGNs must describe legal chess positions. Prompts can describe attributes such
as player strength, opening preferences, or playing style. The conditioning is
probabilistic: it steers the policy rather than enforcing a hard constraint.
Intended use
This checkpoint is intended for research and chess applications involving
prompt-conditioned move prediction, human-like chess modeling, controllable
chess agents, and analysis of language-conditioned policies through chessnets.
It is not a general-purpose language model or a guarantee of engine strength.
Limitations
- Training prompts were produced primarily from synthetic natural-language
templates over game metadata. The model has not been trained on the full
diversity of natural human instructions.
- The learned policy is sensitive to prompt wording, particularly early prompt
tokens. Attention-sink behavior can make superficially similar phrasings
produce different move distributions.
- Out-of-distribution wording, attributes, languages, chess variants, or
contradictory instructions may be ignored or interpreted unpredictably.
- Prompt conditioning is statistical and does not guarantee compliance with a
requested opening, strength, identity, or style.
- Results inherit limitations and biases from the Lichess training data, the
base Lc0 network, ChessGPT, and the prompt-generation process.
Training and evaluation
The model was trained on metadata-augmented Lichess games using generated prompt
templates. Architecture, training, and benchmark details are reported in the
paper. Exact source configuration,
checkpoint provenance, and file hashes are included in
provenance.json and
artifact_manifest.json. This release corresponds to
controlnet_onephase_full_training_run_v2_aux_targets_2018_finetune.
License and upstream models
The
model artifacts in this repository are released under GPL-3.0. This
model is derived from an
Lc0
GPL-3.0 model and the
ChessGPT Apache-2.0 text
model. This model-artifact license does not relicense the separately distributed
UniMaia, chessnets, or chesseval software; consult those repositories for their
code and third-party-file licensing.
Citation
The paper is currently under review. Please use the archival EMNLP Findings
citation if the paper is accepted and that version becomes available; until
then, cite the arXiv version:
1@article{siu2026unimaia,
2 title={UniMaia: Steering Chess Policies with Language for Human-like Play},
3 author={Siu, Sherman and Istead, Lesley},
4 journal={arXiv preprint arXiv:2605.27767},
5 year={2026},
6 doi={10.48550/arXiv.2605.27767}
7}
