Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
dbest-isi
/
searchless-chess-9M-dpo
like
1
Reinforcement Learning
JAX
English
chess
dpo
direct-preference-optimization
haiku
self-play
arxiv:
2402.04494
arxiv:
2305.18290
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
searchless-chess-9M-dpo
/
searchless_chess_code
36.3 kB
1 contributor
History:
1 commit
dbest-isi
Upload searchless chess model
0839651
verified
8 days ago
__init__.py
Safe
31 Bytes
Upload searchless chess model
8 days ago
config.py
Safe
3.14 kB
Upload searchless chess model
8 days ago
constants.py
Safe
3.34 kB
Upload searchless chess model
8 days ago
hf_model.py
Safe
11.6 kB
Upload searchless chess model
8 days ago
tokenizer.py
Safe
3.2 kB
Upload searchless chess model
8 days ago
transformer.py
Safe
9.65 kB
Upload searchless chess model
8 days ago
utils.py
Safe
5.37 kB
Upload searchless chess model
8 days ago