Zeyu Mi

yzmizeyu's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 2 papers 24 days ago

PipeLLM: Fast and Confidential Large Language Model Services with Speculative Pipelined Encryption

Paper • 2411.03357 • Published Nov 4, 2024

SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment

Paper • 2507.20984 • Published 25 days ago • 54

upvoted a paper 25 days ago

SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment

Paper • 2507.20984 • Published 25 days ago • 54

New activity in PowerInfer/SmallThinker-4BA0.6B-Instruct-GGUF 25 days ago

无法复现smallthinker-4ba0.6b在8elite手机上的性能数据

1

#1 opened 26 days ago by

CHNtentes

liked 2 models 26 days ago

PowerInfer/SmallThinker-4BA0.6B-Instruct-GGUF

Text Generation • 4B • Updated 18 days ago • 13.7k • 28

PowerInfer/SmallThinker-21BA3B-Instruct-GGUF

Text Generation • 22B • Updated 18 days ago • 41.4k • 31

liked 2 models 27 days ago

PowerInfer/SmallThinker-4BA0.6B-Instruct

Text Generation • 4B • Updated 22 days ago • 1.25k • 44

PowerInfer/SmallThinker-21BA3B-Instruct

Text Generation • 22B • Updated 22 days ago • 972 • 101

updated 2 models 27 days ago

PowerInfer/SmallThinker-21BA3B-Instruct

Text Generation • 22B • Updated 22 days ago • 972 • 101

PowerInfer/SmallThinker-4BA0.6B-Instruct

Text Generation • 4B • Updated 22 days ago • 1.25k • 44

liked 2 models 8 months ago

bartowski/SmallThinker-3B-Preview-GGUF

Text Generation • 3B • Updated Dec 30, 2024 • 1.07k • 30

PowerInfer/SmallThinker-3B-Preview

Text Generation • 3B • Updated Jan 16 • 32.9k • 410

liked a dataset 8 months ago

PowerInfer/QWQ-LONGCOT-500K

Viewer • Updated Dec 26, 2024 • 286k • 60 • 126

authored 3 papers about 1 year ago

ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs

Paper • 2402.03804 • Published Feb 6, 2024 • 4

Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters

Paper • 2406.05955 • Published Jun 10, 2024 • 28

PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Paper • 2406.06282 • Published Jun 10, 2024 • 39

upvoted 2 papers about 1 year ago

Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters

Paper • 2406.05955 • Published Jun 10, 2024 • 28

PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Paper • 2406.06282 • Published Jun 10, 2024 • 39

liked a model about 1 year ago

PowerInfer/TurboSparse-Mixtral

Feature Extraction • 52B • Updated Jun 14, 2024 • 4 • 35

liked a model over 1 year ago

PowerInfer/Bamboo-base-v0_1

Feature Extraction • 7B • Updated Jun 7, 2024 • 66 • 21