Downloads · 30 days
16
100% of all-time downloads
nebium
nabin2004/nebium
nebium is a machine learning model from nabin2004. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch.
Causal Transformer for self-supervised next-move prediction on chess games.
All-time downloads
16
Public
Repo size
127 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt83.9 MB · 67%
At a glance
- Library
- pytorch
- Access
- Public
- Created
- Aug 25, 2026
- Updated
- Sep 17, 2026
- SHA
- 998c84ae
Spaces
Model card
From the Hugging Face model README
Nebium
Causal Transformer for self-supervised next-move prediction on chess games.
Architecture
- d_model: 512
- n_heads: 8
- n_layers: 6
- vocab_size: 2018
- max_seq_len: 512
- positional_encoding: rope
- activation: swiglu
- norm: rmsnorm
Artifacts & Formats
model.pt: Raw PyTorch state_dictmodel_config.json: Architecture configurationtokenizer.json: BPE Chess tokenizernebium.gguf: GGUF format model for local inference and quantization
Last validation metrics
val/loss: 2.376061725547775val/accuracy: 0.36386593746665474val/top5_accuracy: 0.705297920239525val/perplexity: 10.762433873185277val/legal_move_rate: 0.9833333333333333
- Library
- pytorch
- Created
- Aug 25, 2026
- Updated
- Sep 17, 2026