bolixinyu

Dear ttengwang, I am submitting a pull request to contribute to the Awesome_Long_Form_Video_Understanding with a new work titled "*Towards Long Video Understanding via Fine-detailed Video Story Generation*". This article transforms...

Training instability with InfLLM v2 on MiniCPM4-8B using sparse attention

6

I'm encountering training instability when attempting to fine-tune MiniCPM4-8B using InfLLM v2 with the provided sparse configuration. The training collapses immediately with gradient norm NaN at the first optimization step...