Safetensors
llava
multimodal

clip size not match

#6
by Difei666 - opened

加载clip报错
RuntimeError: Error(s) in loading state_dict for CLIPVisionModel:
size mismatch for vision_model.embeddings.patch_embedding.weight: copying a param with shape torch.Size([1152, 3, 14, 14]) from checkpoint, the shape in current model is torch.Size([768, 3, 32, 32]).)nts。

Difei666 changed discussion title from dependency version? to clip size not match
Difei666 changed discussion status to closed

Sign up or log in to comment