Nguyễn Minh Phúc's picture

4

Nguyễn Minh Phúc

DatPySci

·

AI & ML interests

Reinforcement learning, NLP

Recent Activity

published a model about 2 hours ago

DatPySci/RLDI

updated a model 4 months ago

DatPySci/Qwen-2.5-7B-Simple-RL

published a model 4 months ago

DatPySci/Qwen-2.5-7B-Simple-RL

View all activity

Organizations

DatPySci 's models 91

DatPySci/RLDI

Updated about 2 hours ago

DatPySci/Qwen-2.5-7B-Simple-RL

DatPySci/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

2B • Updated Apr 28 • 5

DatPySci/DeepSeek-Qwen-1.5B-GRPO

2B • Updated Apr 22 • 5

DatPySci/Qwen-1.5B-Math-GRPO

DatPySci/Llama-3.2-3B-sft-mixture

Text Generation • 3B • Updated Feb 10 • 1.71k

DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.01_steps_72000__tldr

Updated Nov 18, 2024

DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.1_steps_32400__tldr

Updated Nov 18, 2024

DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.05_steps_32400__tldr

Updated Nov 18, 2024

DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.01_steps_32400__tldr

Updated Nov 18, 2024

DatPySci/llama3-1b_reward_tldr

Text Classification • 1B • Updated Nov 11, 2024 • 1

DatPySci/EleutherAI_pythia-2.8b-deduped__dpo_pythia-2.8b_beta-0.01__tldr

Updated Sep 30, 2024

DatPySci/EleutherAI_pythia-410m-deduped__ipo_ipo_pythia-1b_beta-0.03__tldr

Updated Sep 28, 2024

DatPySci/EleutherAI_pythia-410m-deduped__length_IS_ipo_pythia-1b_beta-0.03__tldr

Updated Sep 28, 2024

DatPySci/EleutherAI_pythia-410m-deduped__ipo_ipo_pythia-1b_beta-0.02__tldr

Updated Sep 28, 2024

DatPySci/EleutherAI_pythia-410m-deduped__length_IS_ipo_pythia-1b_beta-0.02__tldr

Updated Sep 28, 2024

DatPySci/EleutherAI_pythia-410m-deduped__length_IS_ipo_pythia-1b_beta-0.01__tldr

Updated Sep 28, 2024

DatPySci/EleutherAI_pythia-1b-deduped__length_IS_ipo_pythia-1b_beta-0.02__tldr

Updated Sep 28, 2024

DatPySci/model_step_72000_tldr_summarization

Text Generation • 1B • Updated Sep 28, 2024 • 4

DatPySci/model_step_32400_tldr_summarization

Text Generation • 1B • Updated Sep 28, 2024 • 3

DatPySci/sft_model_tldr_summarization

Text Generation • 1B • Updated Sep 28, 2024 • 3

DatPySci/EleutherAI_pythia-1b-deduped__length_IS_ipo_pythia-1b_beta-0.03__tldr

Updated Sep 27, 2024

DatPySci/EleutherAI_pythia-1b-deduped__length_IS_ipo_pythia-1b_beta-0.01__tldr

Updated Sep 27, 2024

DatPySci/EleutherAI_pythia-1b-deduped__ipo_ipo_pythia-1b_beta-0.04__tldr

Updated Sep 27, 2024

DatPySci/EleutherAI_pythia-1b-deduped__ipo_ipo_pythia-1b_beta-0.05__tldr

Updated Sep 27, 2024

DatPySci/EleutherAI_pythia-1b-deduped__length_IS_ipo_pythia-1b_beta-0.04__tldr

Updated Sep 27, 2024

DatPySci/EleutherAI_pythia-1b-deduped__length_IS_ipo_pythia-1b_beta-0.05__tldr

Updated Sep 26, 2024

DatPySci/EleutherAI_pythia-1b-deduped__ipo_ipo_pythia-1b_beta-0.03__tldr

Updated Sep 26, 2024

DatPySci/EleutherAI_pythia-1b-deduped__ipo_ipo_pythia-1b_beta-0.01__tldr

Updated Sep 26, 2024

DatPySci/EleutherAI_pythia-1b-deduped__expectile_pythia-1b_beta-5.0__tldr

Updated Sep 22, 2024