Compatibility with v5

modeling_intern_vit.py

@@ -3,6 +3,8 @@
 # Copyright (c) 2023 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
+
+import numpy as np
 from typing import Optional, Tuple, Union
 
 import torch
@@ -243,7 +245,7 @@ class InternVisionEncoder(nn.Module):
         super().__init__()
         self.config = config
         # stochastic depth decay rule
-        dpr = [x.item() for x in torch.linspace(0, config.drop_path_rate, config.num_hidden_layers)]
+        dpr = [x for x in np.linspace(0, config.drop_path_rate, config.num_hidden_layers)]
         self.layers = nn.ModuleList([
             InternVisionEncoderLayer(config, dpr[idx]) for idx in range(config.num_hidden_layers)])
         self.gradient_checkpointing = True
@@ -306,6 +308,7 @@ class InternVisionModel(PreTrainedModel):
 
         self.embeddings = InternVisionEmbeddings(config)
         self.encoder = InternVisionEncoder(config)
+        self.post_init()
 
     def resize_pos_embeddings(self, old_size, new_size, patch_size):
         pos_emb = self.embeddings.position_embedding