DatPySci/EleutherAI_pythia-1b-deduped__ipo_ipo_pythia-1b_beta-0.05__tldr
Updated
Nguyễn Minh Phúc
DatPySci
AI & ML interests
Reinforcement learning, NLP
Recent Activity
updated a model about 4 hours ago
DatPySci/knowledge-context-distillation updated a model 2 days ago
DatPySci/pretrain-sharpen published a model 20 days ago
DatPySci/knowledge-context-distillationOrganizations
DatPySci/EleutherAI_pythia-1b-deduped__length_IS_ipo_pythia-1b_beta-0.04__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__length_IS_ipo_pythia-1b_beta-0.05__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__ipo_ipo_pythia-1b_beta-0.03__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__ipo_ipo_pythia-1b_beta-0.01__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__expectile_pythia-1b_beta-5.0__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.1_steps_sft__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.05_steps_sft__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.03_steps_sft__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.01_steps_sft__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__clipped_pythia-1b_beta-0.1__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__ppo__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__clip_pythia-1b_beta-0.1__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_pythia-1b_beta-0.01__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__length_IS_pythia-1b_beta-0.01__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_pythia-1b_beta-0.1__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_pythia-1b_beta-0.05__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_pythia-1b_beta-0.01__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__offline_rl__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_10_sft__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_3_sft__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_1.0_sft__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.3_sft__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.1_sft__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.05_sft__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.03_sft__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.01_steps_46800__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__dpo_shift_beta_0.01_sft__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__pref_shift__tldr
Updated
DatPySci/EleutherAI_pythia-1b-deduped__off_policy__tldr
Updated