Open-weight model

chessard

by Daniel Monroe danielgmonroe/chessard

chessard is an open-weight model from Daniel Monroe, released under gpl-3.0. Its published files total 401.1 MB.

Weights for chessard, a network that predicts the move a human of a given rating would play. It is built on a Leela Chess Zero BT4 transformer body with a Stockfish-aware policy head.

Parameters—

Context—

Weights401.1 MB

Licensegpl-3.0

AccessOpen weights

Monthly Downloads—

Model Card

By Daniel Monroe, published under gpl-3.0, revision 9ceee2352178.

Weights for chessard, a network that predicts the move a human of a given rating would play. It is built on a Leela Chess Zero BT4 transformer body with a Stockfish-aware policy head. The engine and inference code live in the chessard-uci repository; this repo holds only weights. loras/players.json maps each adapter to the player's name and rating; the engine plays a player at that rating unless told otherwise. The adapters are rank-1 LoRA finetunes (float16, ~450 KB each) on that player's games. They only work on top of chessard.pt. Download the whole repo into one folder, then point the engine at it: Instead of --weights-dir you can set CHESSARDDIR=~/chessard-weights once. Every program…

Read Daniel Monroe's full model card

Weights for chessard, a network that predicts the move a human of a given rating would play. It is built on a Leela Chess Zero BT4 transformer body with a Stockfish-aware policy head. The engine and inference code live in the chessard-uci repository; this repo holds only weights.

File	What	Elo (default)
`chessard.pt`	base model (float16, ~400 MB)	2000–2900 (trained on 2000+ games)
`loras/carlsen.pt`	LoRA adapter: Magnus Carlsen	2840
`loras/nakamura.pt`	LoRA adapter: Hikaru Nakamura	2810
`loras/sadler.pt`	LoRA adapter: Matthew Sadler	2692
`loras/janik.pt`	LoRA adapter: Igor Janik	2504
`loras/kaufman.pt`	LoRA adapter: Larry Kaufman	2188

loras/players.json maps each adapter to the player's name and rating; the engine plays a player at that rating unless told otherwise. The adapters are rank-1 LoRA finetunes (float16, ~450 KB each) on that player's games. They only work on top of chessard.pt.

Use

Download the whole repo into one folder, then point the engine at it:

hf download danielgmonroe/chessard --local-dir ~/chessard-weights
./uci.py --weights-dir ~/chessard-weights --player carlsen   # plays at 2840

Instead of --weights-dir you can set CHESSARD_DIR=~/chessard-weights once. Every program that reads it will then share the same copy.

Format

chessard.pt: {"model_state_dict": {...}, "global_step": int}.
loras/<player>.pt: {"adapter_state_dict": {...}, "lora_rank", "lora_alpha", "lora_targets", ...}. To load one, load the base model, wrap each targeted nn.Linear (named by the *.lora_A / *.lora_B keys) as y = Wx + b + (alpha/rank) * B(Ax), then load the adapter state dict with strict=False.

Identity and Version

Repository: danielgmonroe/chessard
Publisher: Daniel Monroe
Task: Not stated by the source
Modality: Other
Library: Not stated by the source
Parameters: Not stated by the source
Languages: uci
Revision: 9ceee2352178bb6a198a3f523c1651c20c87a75a
First published: 2026-10-05
Last updated: 2026-10-05

Files and Weights

9 files, 401.1 MB in total. The weights are 6 files totalling 401.1 MB in pt.

Weights6 files · 401.1 MB

Configuration1 file · 283 B

Documentation1 file · 1.8 KB

Repository1 file · 1.5 KB

Every file

File	Type	Size	SHA-256
chessard.pt	Weights	398.8 MB	199c87c4f694
loras/carlsen.pt	Weights	454.6 KB	2cbe2484348f
loras/janik.pt	Weights	443.2 KB	0506da70bdcb
loras/kaufman.pt	Weights	454.6 KB	75f2cbf5c172
loras/nakamura.pt	Weights	455.3 KB	68c431895518
loras/sadler.pt	Weights	448.5 KB	6409e505f8de
loras/players.json	Configuration	283 B	—
README.md	Documentation	1.8 KB	—
.gitattributes	Repository	1.5 KB	—

License and Download

License: gpl-3.0
Access: Open weights, no gate
Download size: 401.1 MB

Download from Daniel Monroe

Released by Daniel Monroe through its official repository on Hugging Face. Read the license.

Memory Requirements

Precision	Weights in memory
As published	401.1 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About chessard

What license is chessard released under?

gpl-3.0, as its publisher declares it. Read the license text before commercial use.