Nguyễn Minh Phúc
DatPySci
AI & ML interests
Reinforcement learning, NLP
Recent Activity
updated
a dataset
about 10 hours ago
DatPySci/weak_Llama-3.2-1B_tldr_synthetic
updated
a dataset
about 10 hours ago
DatPySci/weak_gpt2-large_tldr_synthetic
updated
a dataset
about 10 hours ago
DatPySci/weak_gpt2-medium_tldr_synthetic
Organizations
Collections
1
models
95
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.1_steps_72000__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.05_steps_72000__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.01_steps_72000__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.1_steps_32400__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.05_steps_32400__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.01_steps_32400__tldr
Updated
DatPySci/llama3-1b_reward_tldr
Text Classification
•
Updated
•
47
DatPySci/EleutherAI_pythia-2.8b-deduped__ipo_pythia-2.8b_beta-0.1__tldr
Updated
DatPySci/EleutherAI_pythia-2.8b-deduped__dpo_pythia-2.8b_beta-0.05__tldr
Updated
DatPySci/EleutherAI_pythia-2.8b-deduped__length_IS_pythia-2.8b_beta-0.05__tldr
Updated
datasets
16
DatPySci/weak_Llama-3.2-1B_tldr_synthetic
Viewer
•
Updated
•
115k
DatPySci/weak_gpt2-large_tldr_synthetic
Viewer
•
Updated
•
115k
DatPySci/weak_gpt2-medium_tldr_synthetic
Viewer
•
Updated
•
115k
DatPySci/weak_gpt2_tldr_synthetic
Viewer
•
Updated
•
115k
DatPySci/synthetic_tldr_sft
Viewer
•
Updated
•
50k
•
17
DatPySci/synthetic_tldr_step_72000
Viewer
•
Updated
•
50k
•
15
DatPySci/synthetic_tldr_step_32400
Viewer
•
Updated
•
50k
•
17
DatPySci/llama3-1b_synthetic_tldr
Viewer
•
Updated
•
115k
•
27
DatPySci/HH-RLHF-preprocessed
Viewer
•
Updated
•
119k
•
42
DatPySci/tldr_preference_dataset
Viewer
•
Updated
•
179k
•
36