Downloads · 30 days
0
chess-position-embedder-onnx
cemoss17/chess-position-embedder-onnx
chess-position-embedder-onnx is a machine learning model from cemoss17. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
ONNX export of the 9M-parameter DeepMind Searchless Chess action-value model, used as a FEN → 768-dim position embedding. The action conditioning is held fixed (action=0) so it contributes a constant offset; we mean-p…
Access
Public
Updated May 19, 2026
Repo size
71.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx35.7 MB · 50%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- May 19, 2026
- Updated
- May 19, 2026
- SHA
- 9b14a1a9
Model card
From the Hugging Face model README
Chess position embedder (ONNX)
ONNX export of the 9M-parameter DeepMind Searchless Chess action-value model, used as a FEN → 768-dim position embedding. The action conditioning is held fixed (action=0) so it contributes a constant offset; we mean-pool the trunk hidden state over the 77 FEN positions to produce a position-only embedding.
Side-to-move is mirrored to white via python-chess before tokenization so embeddings live in a canonical frame.
Files
searchless-9m-mma.onnx— ONNX graph (external data references in.onnx.data)searchless-9m-mma.onnx.data— external tensor weights
Both files must be downloaded side-by-side; the .onnx references the
.onnx.data by relative path.
Provenance
Ported from JAX weights via web/scripts/onnx/port_weights.py and
web/scripts/onnx/export.py. JAX↔ONNX numerical parity was verified to
max abs diff 6.1e-05 on a 128-FEN fixture (web/scripts/onnx/test_parity.py).
- License
- apache-2.0
- Created
- May 19, 2026
- Updated
- May 19, 2026