CogVLM icon indicating copy to clipboard operation
CogVLM copied to clipboard

Published 20 hours ago • verified publisher icon THUDM

CogAgent 视觉预训练模型 EVA2-CLIP-L

Open hzhiyuan opened this issue 1 year ago • 1 comments

想用 CogAgent 的视觉预训练模型，看到 https://github.com/THUDM/SwissArmyTransformer/blob/main/sat/resources/urls.py 里面只有一个名为 eva02_L_pt_m38m_p14 的模型，请问 eva02_L_pt_m38m_p14 就是 CogAgent 的视觉预训练模型吗 @1049451037

hzhiyuan avatar May 10 '24 08:05 hzhiyuan

eva-clip-4b-14-x-drop-last-layer 是CogAgent的预训练初始化，对应 sat/model/official/eva_clip_model.py

eva02_L_pt_m38m_p14 是另一个vit模型，对应 sat/model/official/eva2_model.py

1049451037 avatar Jun 03 '24 01:06 1049451037