Upload folder using huggingface_hub

generation_config.json

@@ -1,4 +1,9 @@
 {
   "_from_model_config": true,
-  "transformers_version": "4.37.2"
+  "transformers_version": "4.37.2",
+  "eos_token_id": [
+    2,
+    6,
+    7
+  ]
 }

modeling_intern_vit.py

@@ -287,9 +287,9 @@ class InternVisionEncoderLayer(nn.Module):
         Args:
             hidden_states (`Tuple[torch.FloatTensor, Optional[torch.FloatTensor]]`): input to the layer of shape `(batch, seq_len, embed_dim)`
         """
-        hidden_states = hidden_states + self.drop_path1(self.attn(self.norm1(hidden_states)) * self.ls1)
+        hidden_states = hidden_states + self.drop_path1(self.attn(self.norm1(hidden_states).to(hidden_states.dtype)) * self.ls1)
 
-        hidden_states = hidden_states + self.drop_path2(self.mlp(self.norm2(hidden_states)) * self.ls2)
+        hidden_states = hidden_states + self.drop_path2(self.mlp(self.norm2(hidden_states).to(hidden_states.dtype)) * self.ls2)
 
         return hidden_states