Hacker News new | ask | show | jobs
by abbaselmas 746 days ago
https://ollama.com/library/llava-llama3 llava-llama3
2 comments
qeternity 746 days ago
That is someone else who has just used the Llava name.

It is not by the original group who have published a series of models under the Llava name.

link
CGamesPlay 746 days ago
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.
link
GaggiX 746 days ago
>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.

link