AI & ML interests
Insanely fast LLM pre-training and fine-tuning for modern NVIDIA GPUs.
Recent Activity
models 37
surogate/Qwen3-1.7B-Libra-MF
Text Generation • 2B • Updated • 70
surogate/Qwen3.5-2B-Libra-YTD
Text Generation • 2B • Updated • 227
surogate/Qwen3.5-9B-NVFP4
Image-Text-to-Text • 7B • Updated • 11 • 1
surogate/Qwen3.5-4B-NVFP4
Image-Text-to-Text • 3B • Updated • 152 • 1
surogate/Qwen3.5-2B-NVFP4
Image-Text-to-Text • 2B • Updated • 2
surogate/Qwen3.5-0.8B-NVFP4
Image-Text-to-Text • 0.7B • Updated • 518
surogate/Qwen3.5-9B-FP8
Image-Text-to-Text • 9B • Updated • 5.03k
surogate/Qwen3.5-4B-FP8
Image-Text-to-Text • 5B • Updated • 188
surogate/Qwen3.5-2B-FP8
Image-Text-to-Text • 2B • Updated • 649 • 1
surogate/Qwen3.5-0.8B-FP8
Image-Text-to-Text • 0.9B • Updated • 367 • 1
datasets 13
surogate/mf-dataset
Viewer • Updated • 6.35k • 12
surogate/ytd-dataset
Viewer • Updated • 3.94k • 20
surogate/hellaswag-ro
Viewer • Updated • 9.25k • 17
surogate/cc-pretrain
Viewer • Updated • 981 • 7
surogate/brd-en
Viewer • Updated • 143 • 7
surogate/brd
Viewer • Updated • 143 • 6
surogate/densemax-self-cognition
Viewer • Updated • 124 • 6
surogate/self-cognition-dan
Viewer • Updated • 2k • 9
surogate/self-cognition-generated
Viewer • Updated • 2k • 10
surogate/self-cognition-qwen3
Viewer • Updated • 50 • 8