Upload app.py

app.py

@@ -4,8 +4,11 @@ from plip_support import embed_text
 import numpy as np
 from PIL import Image
 import requests
+import transformers
+import tokenizers
 from io import BytesIO
 import streamlit as st
+from transformers import CLIPModel
 import clip
 import torch
 from transformers import (
@@ -27,14 +30,20 @@ def embed_texts(model, texts, processor):
         )
     return embeddings
 
-@st.cache_resource
+@st.cache
 def load_embeddings(embeddings_path):
     print("loading embeddings")
     return np.load(embeddings_path)
 
-@st.cache_resource
+@st.cache(
+    hash_funcs={
+        torch.nn.parameter.Parameter: lambda _: None,
+        tokenizers.Tokenizer: lambda _: None,
+        tokenizers.AddedToken: lambda _: None
+    }
+)
 def load_path_clip():
-    model = VisionTextDualEncoderModel.from_pretrained("vinid/plip")
+    model = CLIPModel.from_pretrained("vinid/plip")
     processor = AutoProcessor.from_pretrained("vinid/plip")
     return model, processor