Polina Kuznetcova

kuznetcova's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in Alepach/fixingDPO 9 days ago

Add mixed training set (7k step DPO + 3k fixing DPO samples)

#6 opened 9 days ago by

kuznetcova

Upload training/fixing_dpo_5k_seed42.json with huggingface_hub

1

#5 opened 9 days ago by

kuznetcova

Add fixing DPO step 3 input

1

#4 opened 9 days ago by

kuznetcova

Add fixing DPO pairs

#3 opened 9 days ago by

kuznetcova

Add self-correction generations

#2 opened 9 days ago by

kuznetcova

liked a dataset 14 days ago

Alepach/fixingDPO

Viewer • Updated 9 days ago • 25k • 98 • 2