AI & ML interests
Insanely fast LLM pre-training and fine-tuning for modern NVIDIA GPUs.
Recent Activity
models 27
surogate/Qwen3.5-27B-NVFP4
Text Generation • Updated
• 11
surogate/Qwen3-4B
Text Generation • 4B • Updated
• 11
surogate/Qwen3-1.7B
Text Generation • 2B • Updated
• 8
surogate/Qwen3-0.6B
Text Generation • 0.8B • Updated
• 6
surogate/Qwen3-30B-A3B-FP8
Text Generation • 31B • Updated
• 6
surogate/Qwen3-32B-FP8
Text Generation • 33B • Updated
• 7
surogate/Qwen3-14B-FP8
Text Generation • 15B • Updated
• 3
surogate/Qwen3-8B-FP8
Text Generation • 8B • Updated
• 9
surogate/Qwen3-30B-A3B-Base
Text Generation • 31B • Updated
• 9
surogate/Qwen3-8B-Base
Text Generation • 8B • Updated
• 8
datasets 11
surogate/hellaswag-ro
Viewer
• Updated
• 9.25k • 13
surogate/cc-pretrain
Viewer
• Updated
• 981 • 11
surogate/brd-en
Viewer
• Updated
• 143 • 10
surogate/brd
Viewer
• Updated
• 143 • 8
surogate/densemax-self-cognition
Viewer
• Updated
• 124 • 8
surogate/self-cognition-dan
Viewer
• Updated
• 2k • 6
surogate/self-cognition-generated
Viewer
• Updated
• 2k • 9
surogate/self-cognition-qwen3
Viewer
• Updated
• 50 • 10
surogate/self-cognition
Viewer
• Updated
• 50 • 13
surogate/alpaca-gpt4-data-en
Viewer
• Updated
• 52k • 16