arxiv:2410.07172
lipingzhi PRO
pingzhili
AI & ML interests
efficiency
Recent Activity
updated
a dataset
3 days ago
pingzhili/qwen3-8b-mixed
published
a dataset
3 days ago
pingzhili/qwen3-8b-mixed
updated
a dataset
7 days ago
pingzhili/qwen3-8b-gsm8k
Organizations
models
35
pingzhili/duo-attn-patterns
Updated
pingzhili/moonlight-distill-r1
Updated
pingzhili/olmoe-distill
Updated
pingzhili/olmoe-sft
Updated
pingzhili/olmoe-1b-7b-0125-sft-original-filtered
Updated
pingzhili/olmoe-1b-7b-0125-sft-distilled-moonlight-filtered
Updated
pingzhili/olmoe-1b-7b-0125-sft-distilled-moonlight
Updated
pingzhili/modern-bert-predictor
Updated
pingzhili/llama-moe-megablocks
Updated
pingzhili/text-guided
Updated
datasets
39
pingzhili/qwen3-8b-mixed
Viewer
•
Updated
•
63.9k
•
45
pingzhili/qwen3-8b-gsm8k
Viewer
•
Updated
•
7.47k
•
32
pingzhili/tabmwp
Viewer
•
Updated
•
1k
•
42
pingzhili/math
Viewer
•
Updated
•
12.5k
•
47
pingzhili/r1-qwen-7b-gsm8k
Viewer
•
Updated
•
7.47k
•
14
pingzhili/OpenThoughts-114k-R1-Distill
Viewer
•
Updated
•
114k
•
19
pingzhili/OpenThoughts-114k-SFT
Viewer
•
Updated
•
114k
•
19
pingzhili/sft-r1-distill
Viewer
•
Updated
•
1.68M
•
58
pingzhili/natural-instruction-2.8
Preview
•
Updated
•
22
pingzhili/sft-dataset-original-filtered
Viewer
•
Updated
•
836k
•
12