Romanian-first bilingual (RO/EN), dual-mode reasoner models
AI & ML interests
Insanely fast LLM pre-training and fine-tuning for modern NVIDIA GPUs.
Recent Activity
View all activity
models 40
surogate/Surogate-3.5-9B
Image-Text-to-Text • 10B • Updated • 288 • 1
surogate/Surogate-3.5-4B
Image-Text-to-Text • 5B • Updated • 1.76k • 3
surogate/Surogate-3.5-2B
Image-Text-to-Text • 3B • Updated • 1.73k • 1
surogate/Qwen3.5-4B-FP8
Image-Text-to-Text • 5B • Updated • 15
surogate/Qwen3-1.7B-Libra-MF
Text Generation • 2B • Updated • 79
surogate/Qwen3.5-2B-Libra-YTD
Text Generation • 2B • Updated • 26
surogate/Qwen3.5-9B-NVFP4
Image-Text-to-Text • 7B • Updated • 261 • 1
surogate/Qwen3.5-4B-NVFP4
Image-Text-to-Text • 3B • Updated • 377 • 1
surogate/Qwen3.5-2B-NVFP4
Image-Text-to-Text • 2B • Updated • 7
surogate/Qwen3.5-0.8B-NVFP4
Image-Text-to-Text • 0.7B • Updated • 12
datasets 13
surogate/surogate-onboarding-greeting
Viewer • Updated • 1.03k • 46
surogate/surogate-onboarding-greeting-eval
Viewer • Updated • 24 • 33
surogate/hellaswag-ro
Viewer • Updated • 9.25k • 52 • 1
surogate/cc-pretrain
Viewer • Updated • 981 • 25
surogate/brd-en
Viewer • Updated • 143 • 30
surogate/brd
Viewer • Updated • 143 • 28
surogate/densemax-self-cognition
Viewer • Updated • 124 • 16
surogate/self-cognition-dan
Viewer • Updated • 2k • 67 • 1
surogate/self-cognition-generated
Viewer • Updated • 2k • 61 • 1
surogate/self-cognition-qwen3
Viewer • Updated • 50 • 51 • 1