Llama 3-V: Matching GPT4-V with a 100x smaller model and 500 dollars

Edit (June 3 )— From TwitterFirst of all, we want to sincerely apologize to the original authors of MiniCPM. We wanted Mustafa to make the original statement but have been unable to contact him since yesterday. @siddrrsh and I posted Llama3-v with @mustafaaljadery. Mustafa wrote the entirety of the code for the project. Sid and I were both really excited about multimodal models and liked the archi

[misshiki]

“Llama 3-V: GPT4-V の 100 分の 1 の小型モデルで 500 ドル”