Nguyễn Minh Phúc

DatPySci's activity

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

updated 6 datasets about 16 hours ago

DatPySci/hh_gpt2_large_w2s_feedback

Viewer • Updated about 16 hours ago • 53.8k

DatPySci/hh_gpt2_medium_w2s_feedback

Viewer • Updated about 16 hours ago • 53.8k

DatPySci/hh_gpt2_w2s_feedback

Viewer • Updated about 16 hours ago • 53.8k • 2

DatPySci/tldr_gpt2_large_w2s_feedback

Viewer • Updated about 16 hours ago • 46.4k

DatPySci/tldr_gpt2_medium_w2s_feedback

Viewer • Updated about 16 hours ago • 46.4k

DatPySci/tldr_gpt2_w2s_feedback

Viewer • Updated about 16 hours ago • 46.4k • 3

updated a collection 2 days ago

Weak reward TL;DR

Collection

6 items • Updated 2 days ago

updated 4 datasets 3 days ago

DatPySci/gpt2-medium_dpo_tldr_temp_1_2

Viewer • Updated 3 days ago • 8k • 2

DatPySci/gpt2_dpo_tldr_temp_1_0

Viewer • Updated 3 days ago • 3.88k • 2

DatPySci/gpt2-large_dpo_tldr_temp_1_0

Viewer • Updated 3 days ago • 3.88k • 2

DatPySci/gpt2-medium_dpo_tldr_temp_1_0

Viewer • Updated 3 days ago • 3.88k • 2

updated 2 collections 4 days ago

Weak reward Anthropic-HH

Collection

3 items • Updated 4 days ago

Weak reward TL;DR

Collection

6 items • Updated 2 days ago

updated a collection 5 days ago

Weak reward TL;DR

Collection

6 items • Updated 2 days ago

updated 2 datasets 5 days ago

DatPySci/weak_to_strong_reward_tldr

Viewer • Updated 5 days ago • 94.8k • 33

DatPySci/weak_to_strong_reward_hh

Viewer • Updated 5 days ago • 110k • 23

updated a dataset 8 days ago

DatPySci/gpt2_dpo_anthropic_hh_pref

Viewer • Updated 8 days ago • 128k • 10