arxiv:2410.07172
lipingzhi
pingzhili
AI & ML interests
efficiency
Recent Activity
upvoted a collection 3 days ago
Qwen SAEs liked
a model 3 days ago
adamkarvonen/qwen3-8b-saes liked
a dataset 12 days ago
allenai/olmo-mix-1124 Organizations
models 41
pingzhili/non-ft-llm
Updated
pingzhili/flux.1-dev-ghibli
Updated
pingzhili/flux.1-dev-deepcompressor
Updated
pingzhili/flux.1-dev
Updated
pingzhili/gpt-oss-120b-hybrid
Text Generation • 117B • Updated
• 1
pingzhili/DeepSeek-R1-0528-Qwen3-8B-Hybrid
Text Generation • 8B • Updated
• 1
pingzhili/duo-attn-patterns
Updated
pingzhili/moonlight-distill-r1
Updated
pingzhili/olmoe-distill
Updated
pingzhili/olmoe-sft
Updated
datasets 39
pingzhili/qwen3-8b-mixed
Viewer
• Updated
• 63.9k • 7 • 4
pingzhili/qwen3-8b-gsm8k
Viewer
• Updated
• 7.47k • 7
pingzhili/tabmwp
Viewer
• Updated
• 1k • 10
pingzhili/math
Viewer
• Updated
• 12.5k • 11
pingzhili/r1-qwen-7b-gsm8k
Viewer
• Updated
• 7.47k • 6
pingzhili/OpenThoughts-114k-R1-Distill
Viewer
• Updated
• 114k • 12
pingzhili/OpenThoughts-114k-SFT
Viewer
• Updated
• 114k • 60 • 1
pingzhili/sft-r1-distill
Viewer
• Updated
• 1.68M • 153
pingzhili/natural-instruction-2.8
Preview
• Updated
• 34
pingzhili/sft-dataset-original-filtered
Viewer
• Updated
• 836k • 9