search

CircleRadon / TokenPacker

The code for "TokenPacker: Efficient Visual Projector for Multimodal LLM".
148 stars 6 forks source link

Training dataset #1

Closed Yxxxb closed 2 months ago

Yxxxb commented 2 months ago

Hi authors,

image

Are the experimental results reported in Table 1 trained using miniGemini's training sample data? Or did you only use CC3M and 656K SFT data consistent with LLaVA-1.5.

Thanks.

Yxxxb commented 2 months ago

Oh sry, I got the answer in the readme.