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

Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ... by CGamesPlay on Wednesday May 29, 2024 @06:19AM (#40510360)

This appears to be a Llava model which was then fine-tuned using outputs from Llama 3. If I understand correctly, that would make it Llama-2-based.

[ Parent | on HN ]

Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ... by GaggiX on Wednesday May 29, 2024 @06:31AM (#40510422)

>fine-tuned using outputs from Llama 3.

Llama 3 outputs text and can only see text, this is a vision model.

>that would make it Llama-2-based.

It's based on Llama 3, Llama 2 has nothing to do with it. They took Llama 3 Instruct and CLIP-ViT-Large-patch14-336, train the projection layer first and then later finetuned the Llama 3 checkpoint and train a LoRA for the ViT.

[ Parent | on HN ]