arxiv:2601.05242
Peter Belcak
pbelcak
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 8 hours ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
authored
a paper
about 10 hours ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
liked
a model
15 days ago
ResembleAI/chatterbox-turbo
Organizations
None yet
models
7
pbelcak/gpt2-owt-sbb-295B-80k
Text Generation
•
0.1B
•
Updated
•
1
pbelcak/gpt2-owt-295B-80k
Text Generation
•
0.1B
•
Updated
•
2
pbelcak/gpt2-owt-295B
Text Generation
•
0.1B
•
Updated
•
3
pbelcak/nanogpt
Text Generation
•
0.1B
•
Updated
•
5
pbelcak/gemma_2b_pmc_4gpus_50Ksteps_6
Text Generation
•
3B
•
Updated
•
2
pbelcak/gemma_2b_pmc_short7
Text Generation
•
3B
•
Updated
•
16
pbelcak/UltraFastBERT-1x11-long
0.2B
•
Updated
•
7
•
75
datasets
56
pbelcak/pmc-train-5100000-to-5200000-GemmaTokens
Viewer
•
Updated
•
1.1M
•
24
pbelcak/pmc-train-4900000-to-5000000-GemmaTokens
Viewer
•
Updated
•
1.11M
•
28
pbelcak/pmc-train-4800000-to-4900000-GemmaTokens
Viewer
•
Updated
•
1.07M
•
37
pbelcak/pmc-train-4700000-to-4800000-GemmaTokens
Viewer
•
Updated
•
1.03M
•
18
pbelcak/pmc-train-5000000-to-5100000-GemmaTokens
Viewer
•
Updated
•
1.07M
•
18
pbelcak/pmc-train-5400000-to-5500000-GemmaTokens
Viewer
•
Updated
•
1.05M
•
25
pbelcak/pmc-train-4600000-to-4700000-GemmaTokens
Viewer
•
Updated
•
1.01M
•
20
pbelcak/pmc-train-4500000-to-4600000-GemmaTokens
Viewer
•
Updated
•
970k
•
24
pbelcak/pmc-train-4400000-to-4500000-GemmaTokens
Viewer
•
Updated
•
938k
•
20
pbelcak/pmc-train-5500000-to-5600000-GemmaTokens
Viewer
•
Updated
•
954k
•
19