Xijie Huang

ScarletAce's activity

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

authored a paper about 1 month ago

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training

Paper • 2412.09619 • Published Dec 12, 2024 • 22

upvoted a paper about 1 month ago

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training

Paper • 2412.09619 • Published Dec 12, 2024 • 22

upvoted a paper 3 months ago

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

Paper • 2402.14905 • Published Feb 22, 2024 • 127

liked 4 models 3 months ago

facebook/MobileLLM-1B

Text Generation • Updated Nov 1, 2024 • 7.78k • 111

facebook/MobileLLM-600M

Text Generation • Updated Nov 1, 2024 • 348 • 27

facebook/MobileLLM-350M

Text Generation • Updated Nov 1, 2024 • 184 • 27

facebook/MobileLLM-125M

Text Generation • Updated Nov 1, 2024 • 1.45k • 93

upvoted a collection 3 months ago

MobileLLM

Collection

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 9 items • Updated Nov 27, 2024 • 103

liked a Space 3 months ago

Running on Zero

311

🏃

Stable Diffusion 3.5 Large Turbo

Generate images fast with SD3.5 turbo

upvoted a collection 3 months ago

Stable Diffusion 3.5

Collection

6 items • Updated 9 days ago • 124

upvoted a collection 4 months ago

RoLoRA

Collection

[EMNLP2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization • 3 items • Updated Sep 26, 2024 • 3

updated a collection 4 months ago

RoLoRA

Collection

[EMNLP2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization • 3 items • Updated Sep 26, 2024 • 3

liked a model 4 months ago

ScarletAce/LLaMA3-8B-RoLoRA

Updated Sep 24, 2024 • 15 • 1

authored 3 papers 4 months ago

Boosting LLM Reasoning: Push the Limits of Few-shot Learning with Reinforced In-Context Pruning

Paper • 2312.08901 • Published Dec 14, 2023

CMOSE: Comprehensive Multi-Modality Online Student Engagement Dataset with High-Quality Labels

Paper • 2312.09066 • Published Dec 14, 2023

RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization

Paper • 2407.08044 • Published Jul 10, 2024 • 1