Damn, literally a day after I wrote up my experiments[0] with LLaVA 1.5 and computing image embeddings. Interesting to see the performance with the fine-tuned Mistral-7B variant being pretty close to the one with Vicuna-13B - using Mistral 7B is what BakLLaVA did back with LLaVA 1.5.
[0] https://mildbyte.xyz/blog/llama-cpp-python-llava-gpu-embeddi...