LGAI-EXAONE

/

EXAONE-3.0-7.8B-Instruct

like 371

Follow

LG AI Research 65

Hi, congratulations on releasing this excellent model.
Is there a way to extend the context window of this model beyond 4096 tokens? Say, RoPE scaling (even though I know that this model wasn't trained with RoPE). It would be helpful for RAG applications.
Thank you.