AI & ML interests
Insanely fast LLM pre-training and fine-tuning for modern NVIDIA GPUs.
Recent Activity
models 35
surogate/Qwen3.5-9B-NVFP4
Image-Text-to-Text • 7B • Updated • 157 • 1
surogate/Qwen3.5-4B-NVFP4
Image-Text-to-Text • 3B • Updated • 27 • 1
surogate/Qwen3.5-2B-NVFP4
Image-Text-to-Text • 2B • Updated • 5
surogate/Qwen3.5-0.8B-NVFP4
Image-Text-to-Text • 0.7B • Updated • 98
surogate/Qwen3.5-9B-FP8
Image-Text-to-Text • Updated • 640
surogate/Qwen3.5-4B-FP8
Image-Text-to-Text • Updated • 1.02k
surogate/Qwen3.5-2B-FP8
Image-Text-to-Text • Updated • 111 • 1
surogate/Qwen3.5-0.8B-FP8
Image-Text-to-Text • Updated • 1.68k • 1
surogate/Qwen3.5-27B-NVFP4
Text Generation • Updated • 3.32k
surogate/Qwen3-4B
Text Generation • 4B • Updated • 1
datasets 11
surogate/hellaswag-ro
Viewer • Updated • 9.25k • 7
surogate/cc-pretrain
Viewer • Updated • 981 • 3
surogate/brd-en
Viewer • Updated • 143 • 5
surogate/brd
Viewer • Updated • 143 • 10
surogate/densemax-self-cognition
Viewer • Updated • 124 • 19
surogate/self-cognition-dan
Viewer • Updated • 2k • 58
surogate/self-cognition-generated
Viewer • Updated • 2k • 7
surogate/self-cognition-qwen3
Viewer • Updated • 50 • 13
surogate/self-cognition
Viewer • Updated • 50 • 9
surogate/alpaca-gpt4-data-en
Viewer • Updated • 52k • 14