mit-han-lab / streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
https://arxiv.org/abs/2309.17453
MIT License
6.38k stars 355 forks source link

Using LLaVA model #79

Open JesseZZZZZ opened 2 months ago

JesseZZZZZ commented 2 months ago

Hi! Thank you for your great work. I just wonder, if I want to employ this on other LLMs, like LLaVA, do I have to write my own script ( like "modify_llava.py") or I can simply achieve the goal using simply scripts in this base?

Thank you!!