wangkanai's picture

9 69

wangkanai PRO

wangkanai

·

https://github.com/wangkanai

AI & ML interests

Multimodal, Computer Vision, Natural Language Processing, Reinforcement Learning

Organizations

None yet

Collections 5

View 5 collections

models 58

wangkanai/qwen3-vl-32b-thinking

Image-Text-to-Text • 33B • Updated Nov 5, 2025 • 90 • 2

wangkanai/qwen3-vl-8b-thinking

Image-Text-to-Text • 8B • Updated Nov 5, 2025 • 40 • 1

wangkanai/qwen3-vl-4b-thinking

Image-Text-to-Text • 4B • Updated Nov 5, 2025 • 31 • 1

wangkanai/qwen3-vl-4b-instruct

Image-Text-to-Text • 4B • Updated Nov 5, 2025 • 27 • 1

wangkanai/qwen3-vl-30b-a3b-instruct

Image-Text-to-Text • 31B • Updated Nov 5, 2025 • 186

wangkanai/qwen3-vl-8b-instruct

Image-Text-to-Text • 8B • Updated Nov 4, 2025 • 430 • 4

wangkanai/qwen2.5-vl-32b-instruct

Image-Text-to-Text • 33B • Updated Nov 1, 2025 • 38 • 2

wangkanai/qwen3-vl-2b-thinking

Image-Text-to-Text • 2B • Updated Oct 31, 2025 • 21 • 1

wangkanai/qwen3-vl-2b-instruct

Image-Text-to-Text • 2B • Updated Oct 30, 2025 • 31 • 1

wangkanai/qwen2.5-vl-7b-instruct

Image-Text-to-Text • 8B • Updated Oct 29, 2025 • 301 • 2

datasets 0

None public yet