Nguyễn Minh Phúc

DatPySci

6

·

AI & ML interests

Reinforcement learning, NLP

Recent Activity

updated a dataset about 13 hours ago

DatPySci/Self-Distillation-Qwen3-4B-Thinking-2507-medreason-tokenized

published a dataset about 13 hours ago

DatPySci/Self-Distillation-Qwen3-4B-Thinking-2507-medreason-tokenized

updated a dataset about 13 hours ago

DatPySci/Self-Distillation-Qwen3-4B-Instruct-2507-medreason-tokenized

View all activity

Organizations

DatPySci 's datasets 68

DatPySci/llama3-1b_synthetic_tldr

Viewer • Updated Nov 11, 2024 • 115k • 13

DatPySci/HH-RLHF-preprocessed

Viewer • Updated Oct 3, 2024 • 119k • 15

DatPySci/tldr_preference_dataset

Viewer • Updated Oct 3, 2024 • 179k • 13

DatPySci/tldr_sft_dataset

Viewer • Updated Oct 1, 2024 • 130k • 13

DatPySci/policy_shift_dataset

Viewer • Updated Sep 28, 2024 • 150k • 24

DatPySci/shift_dataset

Viewer • Updated Sep 28, 2024 • 156k • 12

DatPySci/summarize_from_feedback_oai_preprocessing

Viewer • Updated Sep 14, 2024 • 179k • 76

DatPySci/summarize_from_feedback_oai_preprocessing_pythia-6.9b-gold

Viewer • Updated Aug 3, 2024 • 115k • 19