Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
thomas-schweich
/
PAWN
like
0
Other
PyTorch
Rust
English
pawn
chess
transformer
world-model
causal-lm
next-token-prediction
representation-learning
parameter-efficient-finetuning
arxiv:
2401.04679
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
PAWN
/
scripts
279 kB
Ctrl+K
Ctrl+K
3 contributors
History:
32 commits
thomas-schweich
Add RoSA sweep pod setup script
6b87e4a
about 4 hours ago
benchmark_stockfish_nodes.py
6.71 kB
Fix outcome array dtype in ceiling computation, np.asarray in script
about 23 hours ago
check_progress.sh
1.84 kB
Safetensors migration, checkpoint integrity, and multi-model training. (#1)
1 day ago
check_rosa_pod.sh
1.95 kB
Add Lichess dataset extraction pipeline and update pod.sh
about 7 hours ago
compute_theoretical_ceiling.py
6.47 kB
Fix outcome array dtype in ceiling computation, np.asarray in script
about 23 hours ago
eval_accuracy.py
14 kB
Safetensors migration, checkpoint integrity, and multi-model training. (#1)
1 day ago
eval_probes.py
5.03 kB
Add post-training evals, /dev/shm checkpoints, async HF push, and _orig_mod fix
1 day ago
export_hf_repo.py
9.37 kB
Safetensors migration, checkpoint integrity, and multi-model training. (#1)
1 day ago
extract_lichess.sh
4.52 kB
Add Lichess dataset extraction pipeline and update pod.sh
about 7 hours ago
generate_lc0_data.py
10.1 kB
Fix outcome array dtype in ceiling computation, np.asarray in script
about 23 hours ago
generate_stockfish_data.py
16.1 kB
Add UCI engine generation, Parquet data pipeline, and Lc0/Stockfish containers
about 4 hours ago
migrate_sweep.sh
3.3 kB
Add sweep migration script (rsync between pods via local staging)
about 21 hours ago
monitor_training.sh
4.08 kB
Monitor script: show step time, games/sec, ETA from synced metrics
1 day ago
profile_step.py
5.71 kB
Safetensors migration, checkpoint integrity, and multi-model training. (#1)
1 day ago
run_evals_local.py
2.99 kB
Fix terminal position diagnostics: report pad_prob for checkmate/stalemate, not legal_rate
about 12 hours ago
run_evals_toplayer.py
2.81 kB
Fix terminal position diagnostics: report pad_prob for checkmate/stalemate, not legal_rate
about 12 hours ago
setup_lc0_pod.sh
2.21 kB
Add UCI engine generation, Parquet data pipeline, and Lc0/Stockfish containers
about 4 hours ago
setup_rosa_pod.sh
1.95 kB
Add Lichess dataset extraction pipeline and update pod.sh
about 7 hours ago
setup_rosa_sweep.sh
2.34 kB
Add RoSA sweep pod setup script
about 4 hours ago
split_dataset.py
4.07 kB
Add UCI engine generation, Parquet data pipeline, and Lc0/Stockfish containers
about 4 hours ago
sweep.py
6.77 kB
Add RoSA adapter with gradient-informed sparse masks (#3)
about 8 hours ago
train.py
5.45 kB
Architecture sweep: GPU affinity, arch search space, train.py overrides
about 21 hours ago
train_all.py
23.8 kB
Consolidate all training logging through MetricsLogger
1 day ago
train_bottleneck.py
20.2 kB
Add RoSA adapter with gradient-informed sparse masks (#3)
about 8 hours ago
train_film.py
16.9 kB
Add RoSA adapter with gradient-informed sparse masks (#3)
about 8 hours ago
train_hybrid.py
17.5 kB
Add RoSA adapter with gradient-informed sparse masks (#3)
about 8 hours ago
train_lora.py
18 kB
Add RoSA adapter with gradient-informed sparse masks (#3)
about 8 hours ago
train_rosa.py
29.8 kB
Add RoSA adapter with gradient-informed sparse masks (#3)
about 8 hours ago
train_sparse.py
16.7 kB
Add RoSA adapter with gradient-informed sparse masks (#3)
about 8 hours ago
train_tiny.py
18.5 kB
Add RoSA adapter with gradient-informed sparse masks (#3)
about 8 hours ago