Open LetheRiver0 opened 2 months ago
Currently llava-next-interleave didnt support sglang, if you are going to support it, you could refer to this file and create new siglip tokenizer for it. Inside it should have a preprocessor.json
.
https://huggingface.co/lmms-lab/llavanext-qwen-tokenizer/tree/main
Hi, I am using sglang to deploy llava-next-interleave-qwen-7b, but i found there is no preprocessor_config.json for llava-next-interleave-qwen-7b model, could we add this to huggingface? Or do we have some other recommend and efficiency method to deploy it ? Thanks~