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
models 43
surogate/Qwen3.5-4B-SWQ
Image-Text-to-Text • 3B • Updated • 36 • 1
surogate/ambernet-langid
Audio Classification • 29M • Updated • 26 • 1
surogate/Qwen3.5-2B-SWQ
Image-Text-to-Text • 2B • Updated • 18
surogate/Surogate-3.5-9B
Image-Text-to-Text • 10B • Updated • 100 • 2
surogate/Surogate-3.5-4B
Image-Text-to-Text • 5B • Updated • 125 • 4
surogate/Surogate-3.5-2B
Image-Text-to-Text • 3B • Updated • 62 • 1
surogate/Qwen3.5-4B-FP8
Image-Text-to-Text • 5B • Updated • 87
surogate/Qwen3-1.7B-Libra-MF
Text Generation • 2B • Updated • 14
surogate/Qwen3.5-2B-Libra-YTD
Text Generation • 2B • Updated • 13
surogate/Qwen3.5-9B-NVFP4
Image-Text-to-Text • 7B • Updated • 155 • 1
datasets 28
surogate/ro_sft_magpie_mt
Updated
surogate/fineweb2-ro-llm
Viewer • Updated • 1.06M
surogate/HoraVQA
Viewer • Updated • 1.12k
surogate/ro_sft_pixmo_count
Viewer • Updated • 34.6k
surogate/ro_sft_ultrachat
Preview • Updated
surogate/ro_sft_laion
Viewer • Updated • 558k
surogate/ro_sft_pixmo_aa
Viewer • Updated • 133k
surogate/ro_sft_pixmo_points
Viewer • Updated • 188k
surogate/ro_sft_cosyn
Viewer • Updated • 427k
surogate/ro_sft_llava_mix
Viewer • Updated • 625k