Nguyễn Minh Phúc

DatPySci

6

·

AI & ML interests

Reinforcement learning, NLP

Recent Activity

updated a model 1 day ago

DatPySci/AR-Diff

updated a model 3 days ago

DatPySci/Rubric-Hacking

published a model 15 days ago

DatPySci/Rubric-Hacking

View all activity

Organizations

DatPySci 's datasets 73

DatPySci/OpenThoughts-mixture-preprocessed

Viewer • Updated 26 days ago • 114k • 76

DatPySci/OpenThoughts-114k-preprocessed

Viewer • Updated 26 days ago • 114k • 121

DatPySci/Self-Distillation-Qwen2.5-7B-Instruct-medreason-prefix-instruct-tokenized

Viewer • Updated 30 days ago • 32.7k • 46

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

Viewer • Updated 30 days ago • 32.7k • 54

DatPySci/Self-Distillation-Qwen3-8B-medreason-prefix-instruct-tokenized

Viewer • Updated 30 days ago • 32.7k • 42

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

Viewer • Updated Jul 21 • 32.7k • 14

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

Viewer • Updated Jul 21 • 32.7k • 22

DatPySci/Self-Distillation-Qwen3-8B-medreason-tokenized

Viewer • Updated Jul 21 • 32.7k • 17

DatPySci/MedReason-tokenized

Viewer • Updated Jul 21 • 32.7k • 19

DatPySci/Self-Distillation-m23k-tokenized

Viewer • Updated Jul 21 • 23.5k • 19

DatPySci/Self-Distillation-MedReason-tokenized

Viewer • Updated Jul 21 • 32.7k • 18

DatPySci/Self-Distillation-Huatuo-o1-tokenized

Viewer • Updated Jul 21 • 19.7k • 17

DatPySci/Huatuo-o1-tokenized

Viewer • Updated Jul 20 • 19.7k • 16

DatPySci/Qwen2.5-Math-1.5B-deepscaler

Viewer • Updated Sep 16, 2025 • 161k • 11

DatPySci/Qwen2.5-Math-7B-deepscaler

Viewer • Updated Sep 16, 2025 • 161k • 11 • 1

DatPySci/Llama-3.2-3B-deepscaler

Viewer • Updated Sep 16, 2025 • 161k • 8

DatPySci/Llama-3.1-8B-rm-anthropic-hh

Viewer • Updated Feb 10, 2025 • 140k • 15

DatPySci/Llama-3.1-8B-rm-tldr-pref

Viewer • Updated Feb 10, 2025 • 177k • 16

DatPySci/tldr_pythia-6.9b_pref

Viewer • Updated Feb 6, 2025 • 94.9k • 11

DatPySci/tldr_synthetic_llama3_3b_32

Viewer • Updated Jan 24, 2025 • 5.47k • 10

DatPySci/llama3_3b_sft_tldr_synthetic

Viewer • Updated Jan 19, 2025 • 5.47k • 13

DatPySci/weak_gpt2_large_dpo_hh

Viewer • Updated Jan 9, 2025 • 8k • 13

DatPySci/weak_gpt2_medium_dpo_hh

Viewer • Updated Jan 9, 2025 • 8k • 17

DatPySci/weak_gpt2_dpo_hh

Viewer • Updated Jan 9, 2025 • 8k • 10

DatPySci/Llama-3.2-3B_refine_gpt2-large_tldr

Viewer • Updated Jan 8, 2025 • 8k • 16

DatPySci/Llama-3.2-3B_refine_gpt2-medium_tldr

Viewer • Updated Jan 8, 2025 • 8k • 17

DatPySci/Llama-3.2-3B_refine_gpt2_tldr

Viewer • Updated Jan 8, 2025 • 8k • 13

DatPySci/Llama-3.2-1B_refine_gpt2-large_tldr

Viewer • Updated Jan 8, 2025 • 8k • 16

DatPySci/Llama-3.2-1B_refine_gpt2-medium_tldr

Viewer • Updated Jan 8, 2025 • 8k • 13

DatPySci/Llama-3.2-1B_refine_gpt2_tldr

Viewer • Updated Jan 8, 2025 • 8k • 15