search

DLYuanGod / TinyGPT-V

TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
BSD 3-Clause "New" or "Revised" License
1.24k stars 76 forks source link

Size mismatch for stage1 checkpoints #22

Closed wangskyone closed 9 months ago

wangskyone commented 9 months ago

image

llizhaoxu commented 9 months ago

Hi

Thanks for your interest. In demo_v2, your should use Stage4.pth instead of Stage1.pth cause the input training image have different size, and the model input is a little bit different. ( Note: the stage4 is a test version)