Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
THU-KEG
/
LLaDA-8B-BGPO-sudoku
like
1
Follow
Knowledge Engineer Group @ Tsinghua University
103
Reinforcement Learning
Safetensors
English
llada
sudoku
dllm
bgpo
custom_code
arxiv:
2510.11683
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
b691968
LLaDA-8B-BGPO-sudoku
/
tokenizer_config.json
Commit History
Upload folder using huggingface_hub
1a9fe0f
verified
NeoZ123
commited on
Oct 11
NeoZ123
commited on
