Chi Kim

Hope other people chime in, but this might be difficult because LLaVA is finetuned with Vicuna which is finetuned with 70K Chat GPT conversations from ShareGPT. Just a speculation, but...

Folder is empty?

Thanks!!!

It looks like someone is already working on it, but having problem with extreme hallucination. https://github.com/ggerganov/llama.cpp/pull/5093

Is there quantized vision model in gguf format for llama.cpp?

It seems like a lot of people want this. https://github.com/ollama/ollama/issues/1716 and https://github.com/ollama/ollama/issues/3582 Llama.cpp server has POST /tokenize and POST /detokenize now, so hopefully Ollama can just expose the api.

@dhiltgen I'm not sure if this is the same issue, but I'm running Ollama 0.1.31 on MBP 16" m3 64GB running Sonoma 144.4.1. I imported [miqu-1-70b.q5_K_M.gguf](https://huggingface.co/miqudev/miqu-1-70b/blob/main/miqu-1-70b.q5_K_M.gguf) which is 48.8GB. When...

Thanks for the reply. I'm not sure how QT does it, but I've seen QT Apps with status bar accessible on both MacOS as well as Windows.

Actually, I just realized that I'm supposed to edit pretrain.sh and finetune.sh inside the scripts folder. I'd appreciate if someone could help me to edit and point to write things....

Going to close this and open a discussion.