weihongliang

weihongliang's activity

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

liked a Space 5 months ago

Running

Featured

446

FastVLM WebGPU

🍎

446

Real-time video captioning powered by FastVLM

liked 2 Spaces 6 months ago

Running on Zero

Agents

Featured

112

SAM3 Video Segmentation

🐠

112

Track and label objects in videos using text prompts or clicks

Running

3.83k

The Ultra-Scale Playbook

🌌

3.83k

The ultimate guide to training LLM on large GPU Clusters

liked a dataset 6 months ago

HuggingFaceFV/finevideo

Viewer • Updated 9 days ago • 39.5k • 16.7k • 362

liked 4 Spaces 9 months ago

Runtime error

Agents

276

ClearerVoice-Studio (Speech Enhancement, Separation and Extraction)

📈

276

Better AI powered platform to purify your speech signal

Runtime error

Agents

4

VITA 1.5

📉

4

VITA-1.5 demo

Runtime error

Agents

13

Ola

📊

13

Generate text and audio responses from images and videos

Running

Agents

Featured

372

Qwen2.5 Omni 7B Demo

🏆

372

Chat with AI using text, audio, images, and video

liked 5 models 9 months ago

mradermacher/model_requests

Updated Sep 11, 2025 • 165

mradermacher/RC-Qwen2VL-7b-i1-GGUF

8B • Updated Dec 16, 2025 • 2.21k • 2

mradermacher/RC-Qwen2VL-7b-GGUF

8B • Updated Aug 22, 2025 • 581 • 2

mradermacher/RC-Qwen2VL-2b-i1-GGUF

2B • Updated Dec 13, 2025 • 179 • 2

weihongliang/RC-Qwen2VL-7b

8B • Updated Aug 23, 2025 • 14 • 2

liked 2 Spaces 9 months ago

Sleeping

Agents

2

Personalized VQA

🌖

2

Personalized Conversations About Images with RC-MLLM

Sleeping

Agents

2

RCMLLM

🦀

2

Celebrity Recognition and VQA

liked 2 models 9 months ago

weihongliang/RC-Qwen2VL-2b

2B • Updated Aug 23, 2025 • 14 • 1

Qwen/Qwen2-VL-2B-Instruct

Image-Text-to-Text • Updated Jan 12, 2025 • 4.14M • 500

liked a dataset 10 months ago

Yuanshi/Subjects200K

Viewer • Updated Jan 13, 2025 • 207k • 759 • 48

liked a Space 11 months ago

Runtime error

Agents

64

Multi View Diffusion

🧊

64

Generate multi-view images from text or images