Hugging Face's logo

GoodStartLabs
/
ginrummy-qwen3-8b-grpo-lora-v2

Reinforcement Learning
PEFT
Safetensors
gin-rummy
grpo
lora
game-playing
reward-shaping
Model card Files
xet
 Community
ginrummy-qwen3-8b-grpo-lora-v2 / adapter_config.json

Commit History

Run 9: Simplified GRPO, 500 steps, WeakKnocker opponent, shaped rewards
048634e
verified

Alex-GSL commited on