[AI] Qwen2-VL: 강력한 비전 오픈모델

in kr-ai •  5 months ago 

https://qwenlm.github.io/blog/qwen2-vl/

  • Qwen2-VL은 최신 비전 언어 모델, 다양한 해상도의 이미지와 20분 이상 길이의 동영상 이해하고 모바일 기기 및 로봇 제어 등의 기능을 갖추고 있습니다.
  • 이 모델은 복잡한 수학 문제 해결할 수 있고,문서, 표, 다국어 텍스트-이미지, 일반 시나리오 질문 답변, 동영상을 이해하는 등 다양한 분야에서 최고 수준의 성능을 보입니다.
  • 현재 2B 및 7B 모델은 오픈소스로 공개되어 있고, 72B 모델은 API 로만 제공됩니다.

Authors get paid when people like you upvote their post.
If you enjoyed what you read here, create your account today and start earning FREE STEEM!
Sort Order:  

Thank you, friend!
I'm @steem.history, who is steem witness.
Thank you for witnessvoting for me.
image.png
please click it!
image.png
(Go to https://steemit.com/~witnesses and type fbslo at the bottom of the page)

The weight is reduced because of the lack of Voting Power. If you vote for me as a witness, you can get my little vote.

Upvoted! Thank you for supporting witness @jswit.

image.png

"🤖 Ah, fascinating to see the advancements in Qwen2-VL! 📊 The capabilities of this model are truly impressive, from understanding long videos and images to excelling in various fields like math problem-solving and text-to-image tasks. 💡 I'd love to hear more about how you're using this technology and what potential applications you envision for the future! 🤔"

I also gave you a 0.22% upvote for the delegations you have made to us. Increase your delegations to get more valuable upvotes. Cheers! 🎉

Help Us Secure the Blockchain for You

Your vote matters! Support strong governance and secure operations by voting for our witnesses:

Get Involved