Nguyễn Minh Phúc
DatPySci
AI & ML interests
Reinforcement learning, NLP
Recent Activity
updated a dataset about 21 hours ago
DatPySci/OpenThoughts-mixture-preprocessed published a dataset about 21 hours ago
DatPySci/OpenThoughts-mixture-preprocessed updated a dataset about 22 hours ago
DatPySci/OpenThoughts-114k-preprocessedOrganizations
models 98
DatPySci/Shallow-RLVR
2B • Updated • 9
DatPySci/knowledge-context-distillation
Updated
DatPySci/pretrain-sharpen
Updated
DatPySci/RLVR-SGDM-Gap
Updated
DatPySci/LazyNTK
Updated
DatPySci/RLVR-CoTs
Updated
DatPySci/RLM
Updated
DatPySci/PreRLVR-Controlled
Updated
DatPySci/RLDI
2B • Updated • 6
DatPySci/Qwen-2.5-7B-Simple-RL
Updated • 1
datasets 73
DatPySci/OpenThoughts-mixture-preprocessed
Viewer • Updated • 114k
DatPySci/OpenThoughts-114k-preprocessed
Viewer • Updated • 114k
DatPySci/Self-Distillation-Qwen2.5-7B-Instruct-medreason-prefix-instruct-tokenized
Viewer • Updated • 32.7k • 29
DatPySci/Self-Distillation-Qwen3-4B-Thinking-2507-medreason-prefix-instruct-tokenized
Viewer • Updated • 32.7k • 37
DatPySci/Self-Distillation-Qwen3-8B-medreason-prefix-instruct-tokenized
Viewer • Updated • 32.7k • 24
DatPySci/Self-Distillation-Qwen3-4B-Thinking-2507-medreason-tokenized
Viewer • Updated • 32.7k • 37
DatPySci/Self-Distillation-Qwen3-4B-Instruct-2507-medreason-tokenized
Viewer • Updated • 32.7k • 39
DatPySci/Self-Distillation-Qwen3-8B-medreason-tokenized
Viewer • Updated • 32.7k • 33
DatPySci/MedReason-tokenized
Viewer • Updated • 32.7k • 39
DatPySci/Self-Distillation-m23k-tokenized
Viewer • Updated • 23.5k • 33