Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
zhangsj0722
/
E-GRPO
like
0
License:
mit
Model card
Files
Files and versions
xet
Community
main
E-GRPO
/
scoure_code
/
scripts
/
finetune
13.6 kB
1 contributor
History:
1 commit
zhangsj0722
Upload folder using huggingface_hub
58a7e24
verified
2 months ago
finetune_g2rpo_hps.sh
1.57 kB
Upload folder using huggingface_hub
2 months ago
finetune_g2rpo_hps_clip.sh
1.36 kB
Upload folder using huggingface_hub
2 months ago
finetune_g2rpo_hps_clip_merge.sh
1.94 kB
Upload folder using huggingface_hub
2 months ago
finetune_g2rpo_hps_merge.sh
1.63 kB
Upload folder using huggingface_hub
2 months ago
finetune_g2rpo_rfpt.sh
1.74 kB
Upload folder using huggingface_hub
2 months ago
finetune_g2rpo_rlpt.sh
1.64 kB
Upload folder using huggingface_hub
2 months ago
finetune_g2rpo_rlpt_dino.sh
1.87 kB
Upload folder using huggingface_hub
2 months ago
finetune_g2rpo_rlpt_from_noise.sh
1.88 kB
Upload folder using huggingface_hub
2 months ago