Unchun Yang

ucyang's activity

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

liked a dataset about 3 hours ago

openSUSE/cve-backport-codegen-dataset

Viewer • Updated 2 days ago • 38k • 43 • 1

liked 2 models about 3 hours ago

openSUSE/CVE-Backport-Qwen2.5-Coder-32B

Text Generation • 33B • Updated 2 days ago • 70 • 2

openSUSE/Cavil-Qwen3.5-4B

Text Generation • 5B • Updated 24 days ago • 28 • 1

upvoted a paper about 8 hours ago

LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models

Paper • 2310.08659 • Published Oct 12, 2023 • 29

liked 2 models about 8 hours ago

LoftQ/Meta-Llama-3-8B-Instruct-4bit-64rank

Text Generation • 8B • Updated May 3, 2024 • 4 • 2

LoftQ/Meta-Llama-3-8B-4bit-64rank

Text Generation • 8B • Updated May 3, 2024 • 1.3k • 2

upvoted a collection about 8 hours ago

LoftQ Llama 3

Collection

LoftQ initialization for Llama-3 series • 4 items • Updated May 2, 2024 • 1

liked a model about 13 hours ago

huggingface/documentation-images

Updated Feb 4 • 15

liked 2 Spaces about 13 hours ago

Running on Zero

MCP

2.81k

Z Image Turbo

🖼

2.81k

Generate high-quality images from text prompts

Running

Featured

179

Voxtral TTS Demo

⚡

179

Generate realistic speech from text with custom or preset voices

liked 2 datasets about 13 hours ago

TeichAI/Claude-Opus-4.6-Reasoning-887x

Viewer • Updated about 9 hours ago • 887 • 6.64k • 61

OpenMOSS-Team/OmniAction

Updated 10 days ago • 22.4k • 248

upvoted a collection about 13 hours ago

RoboOmni

Collection

Proactive Robot Manipulation in Omni-modal Context • 9 items • Updated 13 days ago • 12

upvoted a paper about 13 hours ago

RoboOmni: Proactive Robot Manipulation in Omni-modal Context

Paper • 2510.23763 • Published Oct 27, 2025 • 61

liked a dataset about 13 hours ago

OpenMOSS-Team/OmniAction-LIBERO

Updated 10 days ago • 767 • 69

upvoted an article 1 day ago

view article

Article

Preference Tuning LLMs with Direct Preference Optimization Methods

• 
• 
• +3

Jan 18, 2024

•

81

liked a Space 2 days ago

Running on Zero

40

VOID

👀

40

VOID: Video Object and Interaction Deletion

liked a model 2 days ago

netflix/void-model

Video-to-Video • Updated 3 days ago • 425

liked 2 datasets 2 days ago

Junnos/luckyvicky-DPO

Viewer • Updated Jul 10, 2024 • 150 • 35 • 2

stepfun-ai/Step-3.5-Flash-SFT

Viewer • Updated 23 days ago • 1.62M • 56k • 298