It has more in common with GPT-3 than GPT-4 in terms of size, but in reality it's based on Vicuna/Llama which is 10x smaller than either, so as far as the LLM part of it goes its not mini-anything - it's just straight-up Vicuna 13B.
The model as a whole is just BLIP-2 with a larger linear layer, and using Vicuna as the LLM. If you look at their code it's literally using the entire BLIP-2 encoder (Salesforce code).
The model as a whole is just BLIP-2 with a larger linear layer, and using Vicuna as the LLM. If you look at their code it's literally using the entire BLIP-2 encoder (Salesforce code).
https://arxiv.org/pdf/2301.12597.pdf