Hugging Face's logo

brikdavies
/
deepscaleR

Reinforcement Learning
Safetensors
grpo
gdpo
math
lora
qwen3
Model card Files
xet
 Community
deepscaleR / gdpo_lambda0.005_from_lambda0.03_ckpt150
1.25 GB
  • 1 contributor
 History: 6 commits
brikdavies's picture
brikdavies
Upload folder using huggingface_hub
89c075b verified