Nguyễn Minh Phúc

DatPySci

6

·

AI & ML interests

Reinforcement learning, NLP

Recent Activity

updated a model 3 days ago

DatPySci/pretrain-sharpen

updated a model 13 days ago

DatPySci/knowledge-context-distillation

published a model 13 days ago

DatPySci/knowledge-context-distillation

View all activity

Organizations

DatPySci 's datasets 60

DatPySci/base_llama3-1b_anthropic_hh

Viewer • Updated Dec 26, 2024 • 8k • 7

DatPySci/gpt2-large_dpo_anthropic_hh

Viewer • Updated Dec 25, 2024 • 8k • 7

DatPySci/gpt2-medium_dpo_anthropic_hh

Viewer • Updated Dec 25, 2024 • 8k • 8

DatPySci/gpt2_dpo_anthropic_hh

Viewer • Updated Dec 25, 2024 • 8k • 8

DatPySci/base_anthropic_hh

Viewer • Updated Dec 25, 2024 • 219k • 7

DatPySci/llama3-1b_dpo_tldr

Viewer • Updated Dec 21, 2024 • 8k • 5

DatPySci/gpt2-large_dpo_tldr

Viewer • Updated Dec 21, 2024 • 8k • 4

DatPySci/gpt2-medium_dpo_tldr

Viewer • Updated Dec 21, 2024 • 8k • 4

DatPySci/gpt2_dpo_tldr

Viewer • Updated Dec 21, 2024 • 8k • 8

DatPySci/tldr-preference-llama3-8b

Viewer • Updated Dec 21, 2024 • 103k • 6

DatPySci/gsm8k_llama3-1b-instruct

Viewer • Updated Dec 17, 2024 • 7.47k • 4

DatPySci/weak_Llama-3.2-3B_hh

Viewer • Updated Dec 10, 2024 • 8k • 4

DatPySci/weak_Llama-3.2-1B_hh

Viewer • Updated Dec 10, 2024 • 8k • 5

DatPySci/weak_gpt2-large_hh

Viewer • Updated Dec 10, 2024 • 8k • 4

DatPySci/weak_gpt2-medium_hh

Viewer • Updated Dec 10, 2024 • 8k • 4

DatPySci/weak_gpt2_hh

Viewer • Updated Dec 10, 2024 • 8k • 4

DatPySci/weak_gpt2-large_tldr_synthetic

Viewer • Updated Nov 24, 2024 • 115k • 5

DatPySci/weak_gpt2-medium_tldr_synthetic

Viewer • Updated Nov 24, 2024 • 115k • 5

DatPySci/weak_gpt2_tldr_synthetic

Viewer • Updated Nov 24, 2024 • 115k • 5

DatPySci/synthetic_tldr_sft

Viewer • Updated Nov 18, 2024 • 50k • 4

DatPySci/synthetic_tldr_step_72000

Viewer • Updated Nov 18, 2024 • 50k • 161

DatPySci/synthetic_tldr_step_32400

Viewer • Updated Nov 18, 2024 • 50k • 5

DatPySci/llama3-1b_synthetic_tldr

Viewer • Updated Nov 11, 2024 • 115k • 5

DatPySci/HH-RLHF-preprocessed

Viewer • Updated Oct 3, 2024 • 119k • 8

DatPySci/tldr_preference_dataset

Viewer • Updated Oct 3, 2024 • 179k • 5

DatPySci/tldr_sft_dataset

Viewer • Updated Oct 1, 2024 • 130k • 6

DatPySci/policy_shift_dataset

Viewer • Updated Sep 28, 2024 • 150k • 7

DatPySci/shift_dataset

Viewer • Updated Sep 28, 2024 • 156k • 5

DatPySci/summarize_from_feedback_oai_preprocessing

Viewer • Updated Sep 14, 2024 • 179k • 53

DatPySci/summarize_from_feedback_oai_preprocessing_pythia-6.9b-gold

Viewer • Updated Aug 3, 2024 • 115k • 5