How to get this model working with vLLM?

#5
by ququwowo - opened

Hey everyone! 👋

@HaoFeng2025
@xfey

I was wondering how to get this model working with vLLM. Is it as simple as running vllm serve "ByteDance/Dolphin"?

Also, how would I then call the server for both page-level and element-level parsing? If you have any demo code, that would be super helpful!

Thanks a bunch! 😊

x2 🚀

or another serving engine (?)

Same here. Any update ?

Sign up or log in to comment