Peter Belcak's picture

4 14 5

Peter Belcak

pbelcak

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

authored a paper 3 days ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

liked a model 17 days ago

ResembleAI/chatterbox-turbo

View all activity

Organizations

None yet

pbelcak 's models 7

pbelcak/gpt2-owt-sbb-295B-80k

Text Generation • 0.1B • Updated Jul 9, 2024 • 1

pbelcak/gpt2-owt-295B-80k

Text Generation • 0.1B • Updated Jul 9, 2024 • 1

pbelcak/gpt2-owt-295B

Text Generation • 0.1B • Updated Jul 8, 2024 • 3

pbelcak/nanogpt

Text Generation • 0.1B • Updated Jul 5, 2024 • 4

pbelcak/gemma_2b_pmc_4gpus_50Ksteps_6

Text Generation • 3B • Updated May 1, 2024 • 2

pbelcak/gemma_2b_pmc_short7

Text Generation • 3B • Updated Apr 30, 2024 • 15

pbelcak/UltraFastBERT-1x11-long

0.2B • Updated Nov 22, 2023 • 6 • 75